Computer Science › Artificial Intelligence

AI in cancer detection

Works Count: 55760

Wikipedia

Description

This cluster of papers focuses on the application of deep learning and machine learning techniques in medical image analysis, particularly in the context of histopathology images, digital pathology, and computer-aided detection for breast cancer diagnosis. The use of convolutional neural networks and whole slide imaging is prominent in these studies, aiming to improve accuracy and efficiency in cancer prognosis and prediction.

Keywords

Deep Learning; Medical Image Analysis; Histopathology Images; Computer-Aided Detection; Convolutional Neural Networks; Digital Pathology; Breast Cancer Diagnosis; Machine Learning; Whole Slide Imaging; Cancer Prognosis

Multisurface method of pattern separation for medical diagnosis applied to breast cytology.

1990-12-01

William H. Wolberg , O. L. Mangasarian

Multisurface pattern separation is a mathematical method for distinguishing between elements of two pattern sets. Each element of the pattern sets is comprised of various scalar observations. In this paper, … Multisurface pattern separation is a mathematical method for distinguishing between elements of two pattern sets. Each element of the pattern sets is comprised of various scalar observations. In this paper, we use the diagnosis of breast cytology to demonstrate the applicability of this method to medical diagnosis and decision making. Each of 11 cytological characteristics of breast fine-needle aspirates reported to differ between benign and malignant samples was graded 1 to 10 at the time of sample collection. Nine characteristics were found to differ significantly between benign and malignant samples. Mathematically, these values for each sample were represented by a point in a nine-dimensional space of real variables. Benign points were separated from malignant ones by planes determined by linear programming. Correct separation was accomplished in 369 of 370 samples (201 benign and 169 malignant). In the one misclassified malignant case, the fine-needle aspirate cytology was so definitely benign and the cytology of the excised cancer so definitely malignant that we believe the tumor was missed on aspiration. Our mathematical method is applicable to other medical diagnostic and decision-making problems.

View PDF Chat

Predicting breast cancer survivability: a comparison of three data mining methods

2004-09-10

Dursun Delen , Glenn Walker , Amit Kadam

IHC Profiler: An Open Source Plugin for the Quantitative Evaluation and Automated Scoring of Immunohistochemistry Images of Human Tissue Samples

2014-05-06

Frency Varghese , Amirali B. Bukhari , Renu Malhotra +1 more

In anatomic pathology, immunohistochemistry (IHC) serves as a diagnostic and prognostic method for identification of disease markers in tissue samples that directly influences classification and grading the disease, influencing patient … In anatomic pathology, immunohistochemistry (IHC) serves as a diagnostic and prognostic method for identification of disease markers in tissue samples that directly influences classification and grading the disease, influencing patient management. However, till today over most of the world, pathological analysis of tissue samples remained a time-consuming and subjective procedure, wherein the intensity of antibody staining is manually judged and thus scoring decision is directly influenced by visual bias. This instigated us to design a simple method of automated digital IHC image analysis algorithm for an unbiased, quantitative assessment of antibody staining intensity in tissue sections. As a first step, we adopted the spectral deconvolution method of DAB/hematoxylin color spectra by using optimized optical density vectors of the color deconvolution plugin for proper separation of the DAB color spectra. Then the DAB stained image is displayed in a new window wherein it undergoes pixel-by-pixel analysis, and displays the full profile along with its scoring decision. Based on the mathematical formula conceptualized, the algorithm is thoroughly tested by analyzing scores assigned to thousands (n = 1703) of DAB stained IHC images including sample images taken from human protein atlas web resource. The IHC Profiler plugin developed is compatible with the open resource digital image analysis software, ImageJ, which creates a pixel-by-pixel analysis profile of a digital IHC image and further assigns a score in a four tier system. A comparison study between manual pathological analysis and IHC Profiler resolved in a match of 88.6% (P<0.0001, CI = 95%). This new tool developed for clinical histopathological sample analysis can be adopted globally for scoring most protein targets where the marker protein expression is of cytoplasmic and/or nuclear type. We foresee that this method will minimize the problem of inter-observer variations across labs and further help in worldwide patient stratification potentially benefitting various multinational clinical trial initiatives.

View PDF Chat

ROC Methodology in Radiologic Imaging

1986-09-01

Charles E. Metz

If the performance of a diagnostic imaging system is to be evaluated objectively and meaningfully, one must compare radiologists' image-based diagnoses with actual states of disease and health in a … If the performance of a diagnostic imaging system is to be evaluated objectively and meaningfully, one must compare radiologists' image-based diagnoses with actual states of disease and health in a way that distinguishes between the inherent diagnostic capacity of the radiologists' interpretations of the images, and any tendencies to "under-read" or "over-read". ROC methodology provides the only known basis for distinguishing between these two aspects of diagnostic performance. After identifying the fundamental issues that motivate ROC analysis, this article develops ROC concepts in an intuitive way. The requirements of a valid ROC study and practical techniques for ROC data collection and data analysis are sketched briefly. A survey of the radiologic literature indicates the broad variety of evaluation studies in which ROC analysis has been employed.

How To Build and Interpret a Nomogram for Cancer Prognosis

2008-03-06

Alexia Iasonos , Deborah Schrag , Ganesh V. Raj +1 more

Nomograms are widely used for cancer prognosis, primarily because of their ability to reduce statistical predictive models into a single numerical estimate of the probability of an event, such as … Nomograms are widely used for cancer prognosis, primarily because of their ability to reduce statistical predictive models into a single numerical estimate of the probability of an event, such as death or recurrence, that is tailored to the profile of an individual patient. User-friendly graphical interfaces for generating these estimates facilitate the use of nomograms during clinical encounters to inform clinical decision making. However, the statistical underpinnings of these models require careful scrutiny, and the degree of uncertainty surrounding the point estimates requires attention. This guide provides a nonstatistical audience with a methodological approach for building, interpreting, and using nomograms to estimate cancer prognosis or other health outcomes.

A method of comparing the areas under receiver operating characteristic curves derived from the same cases.

1983-09-01

J A Hanley , Barbara J. McNeil

Receiver operating characteristic (ROC) curves are used to describe and compare the performance of diagnostic technology and diagnostic algorithms. This paper refines the statistical comparison of the areas under two … Receiver operating characteristic (ROC) curves are used to describe and compare the performance of diagnostic technology and diagnostic algorithms. This paper refines the statistical comparison of the areas under two ROC curves derived from the same set of patients by taking into account the correlation between the areas that is induced by the paired nature of the data. The correspondence between the area under an ROC curve and the Wilcoxon statistic is used and underlying Gaussian distributions (binormal) are assumed to provide a table that converts the observed correlations in paired ratings of images into a correlation between the two ROC areas. This between-area correlation can be used to reduce the standard error (uncertainty) about the observed difference in areas. This correction for pairing, analogous to that used in the paired t-test, can produce a considerable increase in the statistical sensitivity (power) of the comparison. For studies involving multiple readers, this method provides a measure of a component of the sampling variation that is otherwise difficult to obtain.

Histopathological Image Analysis: A Review

2009-01-01

Metin N. Gürcan , Laura E. Boucheron , Ali Can +3 more

Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent … Over the past decade, dramatic increases in computational power and improvement in image analysis algorithms have allowed the development of powerful computer-assisted analytical approaches to radiological data. With the recent advent of whole slide digital scanners, tissue histopathology slides can now be digitized and stored in digital image form. Consequently, digitized tissue histopathology has now become amenable to the application of computerized image analysis and machine learning techniques. Analogous to the role of computer-assisted diagnosis (CAD) algorithms in medical imaging to complement the opinion of a radiologist, CAD algorithms have begun to be developed for disease detection, diagnosis, and prognosis prediction to complement the opinion of the pathologist. In this paper, we review the recent state of the art CAD technology for digitized histopathology. This paper also briefly describes the development and application of novel image analysis technology for a few specific histopathology related problems being pursued in the United States and Europe.

View PDF Chat

Machine learning applications in cancer prognosis and prediction

2014-11-17

Κωνσταντίνα Κούρου , Themis P. Exarchos , Konstantinos Exarchos +2 more

Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as … Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into high or low risk groups has led many research teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs) and Decision Trees (DTs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we present a review of recent ML approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised ML techniques as well as on different input features and data samples. Given the growing trend on the application of ML methods in cancer research, we present here the most recent publications that employ these techniques as an aim to model cancer risk or patient outcomes.

View PDF Chat

Diagnostic Performance of Digital versus Film Mammography for Breast-Cancer Screening

2005-09-17

Etta D. Pisano , Constantine Gatsonis , Edward Hendrick +7 more

Film mammography has limited sensitivity for the detection of breast cancer in women with radiographically dense breasts. We assessed whether the use of digital mammography would avoid some of these … Film mammography has limited sensitivity for the detection of breast cancer in women with radiographically dense breasts. We assessed whether the use of digital mammography would avoid some of these limitations.

View PDF Chat

Supervised Risk Predictor of Breast Cancer Based on Intrinsic Subtypes

2009-02-10

Joel S. Parker , Michael E. Mullins , Maggie C.U. Cheang +7 more

Purpose To improve on current standards for breast cancer prognosis and prediction of chemotherapy benefit by developing a risk model that incorporates the gene expression–based “intrinsic” subtypes luminal A, luminal … Purpose To improve on current standards for breast cancer prognosis and prediction of chemotherapy benefit by developing a risk model that incorporates the gene expression–based “intrinsic” subtypes luminal A, luminal B, HER2-enriched, and basal-like. Methods A 50-gene subtype predictor was developed using microarray and quantitative reverse transcriptase polymerase chain reaction data from 189 prototype samples. Test sets from 761 patients (no systemic therapy) were evaluated for prognosis, and 133 patients were evaluated for prediction of pathologic complete response (pCR) to a taxane and anthracycline regimen. Results The intrinsic subtypes as discrete entities showed prognostic significance (P = 2.26E-12) and remained significant in multivariable analyses that incorporated standard parameters (estrogen receptor status, histologic grade, tumor size, and node status). A prognostic model for node-negative breast cancer was built using intrinsic subtype and clinical information. The C-index estimate for the combined model (subtype and tumor size) was a significant improvement on either the clinicopathologic model or subtype model alone. The intrinsic subtype model predicted neoadjuvant chemotherapy efficacy with a negative predictive value for pCR of 97%. Conclusion Diagnosis by intrinsic subtype adds significant prognostic and predictive information to standard parameters for patients with breast cancer. The prognostic properties of the continuous risk score will be of value for the management of node-negative breast cancers. The subtypes and risk score can also be used to assess the likelihood of efficacy from neoadjuvant chemotherapy.

View PDF Chat

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

2013-01-01

Dan Cireşan , Alessandro Giusti , Luca Maria Gambardella +1 more

Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images

2016-02-04

Korsuk Sirinukunwattana , Shan E Ahmed Raza , Yee‐Wah Tsang +3 more

Detection and classification of cell nuclei in histopathology images of cancerous tissue stained with the standard hematoxylin and eosin stain is a challenging task due to cellular heterogeneity. Deep learning … Detection and classification of cell nuclei in histopathology images of cancerous tissue stained with the standard hematoxylin and eosin stain is a challenging task due to cellular heterogeneity. Deep learning approaches have been shown to produce encouraging results on histopathology images in various studies. In this paper, we propose a Spatially Constrained Convolutional Neural Network (SC-CNN) to perform nucleus detection. SC-CNN regresses the likelihood of a pixel being the center of a nucleus, where high probability values are spatially constrained to locate in the vicinity of the centers of nuclei. For classification of nuclei, we propose a novel Neighboring Ensemble Predictor (NEP) coupled with CNN to more accurately predict the class label of detected cell nuclei. The proposed approaches for detection and classification do not require segmentation of nuclei. We have evaluated them on a large dataset of colorectal adenocarcinoma images, consisting of more than 20,000 annotated nuclei belonging to four different classes. Our results show that the joint detection and classification of the proposed SC-CNN and NEP produces the highest average F1 score as compared to other recently published approaches. Prospectively, the proposed methods could offer benefit to pathology practice in terms of quantitative analysis of tissue constituents in whole-slide images, and potentially lead to a better understanding of cancer.

View PDF Chat

A Dataset for Breast Cancer Histopathological Image Classification

2015-10-30

Fábio Alexandre Spanhol , Luiz S. Oliveira , Caroline Petitjean +1 more

Today, medical image analysis papers require solid experiments to prove the usefulness of proposed methods. However, experiments are often performed on data selected by the researchers, which may come from … Today, medical image analysis papers require solid experiments to prove the usefulness of proposed methods. However, experiments are often performed on data selected by the researchers, which may come from different institutions, scanners, and populations. Different evaluation measures may be used, making it difficult to compare the methods. In this paper, we introduce a dataset of 7909 breast cancer histopathology images acquired on 82 patients, which is now publicly available from http://web.inf.ufpr.br/vri/breast-cancer-database. The dataset includes both benign and malignant images. The task associated with this dataset is the automated classification of these images in two classes, which would be a valuable computer-aided diagnosis tool for the clinician. In order to assess the difficulty of this task, we show some preliminary results obtained with state-of-the-art image classification systems. The accuracy ranges from 80% to 85%, showing room for improvement is left. By providing this dataset and a standardized evaluation protocol to the scientific community, we hope to gather researchers in both the medical and the machine learning field to advance toward this clinical application.

Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique

2016-04-29

Hayit Greenspan , Bram van Ginneken , Ronald M. Summers

The papers in this special section focus on the technology and applications supported by deep learning. Deep learning is a growing trend in general data analysis and has been termed … The papers in this special section focus on the technology and applications supported by deep learning. Deep learning is a growing trend in general data analysis and has been termed one of the 10 breakthrough technologies of 2013. Deep learning is an improvement of artificial neural networks, consisting of more layers that permit higher levels of abstraction and improved predictions from data. To date, it is emerging as the leading machine-learning tool in the general imaging and computer vision domains. In particular, convolutional neural networks (CNNs) have proven to be powerful tools for a broad range of computer vision tasks. Deep CNNs automatically learn mid-level and high-level abstractions obtained from raw data (e.g., images). Recent results indicate that the generic descriptors extracted from CNNs are extremely effective in object recognition and localization in natural images. Medical image analysis groups across the world are quickly entering the field and applying CNNs and other deep learning methodologies to a wide variety of applications.

Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis

2016-05-23

Geert Litjens , Clara I. Sá‎nchez , N. K. Timofeeva +7 more

Abstract Pathologists face a substantial increase in workload and complexity of histopathologic cancer diagnosis due to the advent of personalized medicine. Therefore, diagnostic protocols have to focus equally on efficiency … Abstract Pathologists face a substantial increase in workload and complexity of histopathologic cancer diagnosis due to the advent of personalized medicine. Therefore, diagnostic protocols have to focus equally on efficiency and accuracy. In this paper we introduce ‘deep learning’ as a technique to improve the objectivity and efficiency of histopathologic slide analysis. Through two examples, prostate cancer identification in biopsy specimens and breast cancer metastasis detection in sentinel lymph nodes, we show the potential of this new methodology to reduce the workload for pathologists, while at the same time increasing objectivity of diagnoses. We found that all slides containing prostate cancer and micro- and macro-metastases of breast cancer could be identified automatically while 30–40% of the slides containing benign and normal tissue could be excluded without the use of any additional immunohistochemical markers or human intervention. We conclude that ‘deep learning’ holds great promise to improve the efficacy of prostate cancer diagnosis and breast cancer staging.

View PDF Chat

Image analysis and machine learning in digital pathology: Challenges and opportunities

2016-07-04

Anant Madabhushi , George Lee

View PDF Chat

Large scale deep learning for computer aided detection of mammographic lesions

2016-08-03

Thijs Kooi , Geert Litjens , Bram van Ginneken +5 more

View PDF Chat

Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases

2016-01-01

Andrew Janowczyk , Anant Madabhushi

Background: Deep learning (DL) is a representation learning approach ideally suited for image analysis challenges in digital pathology (DP). The variety of image analysis tasks in the context of DP … Background: Deep learning (DL) is a representation learning approach ideally suited for image analysis challenges in digital pathology (DP). The variety of image analysis tasks in the context of DP includes detection and counting (e.g., mitotic events), segmentation (e.g., nuclei), and tissue classification (e.g., cancerous vs. non-cancerous). Unfortunately, issues with slide preparation, variations in staining and scanning across sites, and vendor platforms, as well as biological variance, such as the presentation of different grades of disease, make these image analysis tasks particularly challenging. Traditional approaches, wherein domain-specific cues are manually identified and developed into task-specific “handcrafted” features, can require extensive tuning to accommodate these variances. However, DL takes a more domain agnostic approach combining both feature discovery and implementation to maximally discriminate between the classes of interest. While DL approaches have performed well in a few DP related image analysis tasks, such as detection and tissue classification, the currently available open source tools and tutorials do not provide guidance on challenges such as (a) selecting appropriate magnification, (b) managing errors in annotations in the training (or learning) dataset, and (c) identifying a suitable training set containing information rich exemplars. These foundational concepts, which are needed to successfully translate the DL paradigm to DP tasks, are non-trivial for (i) DL experts with minimal digital histology experience, and (ii) DP and image processing experts with minimal DL experience, to derive on their own, thus meriting a dedicated tutorial. Aims: This paper investigates these concepts through seven unique DP tasks as use cases to elucidate techniques needed to produce comparable, and in many cases, superior to results from the state-of-the-art hand-crafted feature-based classification approaches. Results: Specifically, in this tutorial on DL for DP image analysis, we show how an open source framework (Caffe), with a singular network architecture, can be used to address: (a) nuclei segmentation (F-score of 0.83 across 12,000 nuclei), (b) epithelium segmentation (F-score of 0.84 across 1735 regions), (c) tubule segmentation (F-score of 0.83 from 795 tubules), (d) lymphocyte detection (F-score of 0.90 across 3064 lymphocytes), (e) mitosis detection (F-score of 0.53 across 550 mitotic events), (f) invasive ductal carcinoma detection (F-score of 0.7648 on 50 k testing patches), and (g) lymphoma classification (classification accuracy of 0.97 across 374 images). Conclusion: This paper represents the largest comprehensive study of DL approaches in DP to date, with over 1200 DP images used during evaluation. The supplemental online material that accompanies this paper consists of step-by-step instructions for the usage of the supplied source code, trained models, and input data.

View PDF Chat

Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features

2016-08-16

Kun‐Hsing Yu , Ce Zhang , Gerald J. Berry +4 more

Abstract Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients’ prognoses. In this … Abstract Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients’ prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma ( P <0.003) or squamous cell carcinoma ( P =0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort ( P <0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs.

View PDF Chat

Deep Learning in Medical Image Analysis

2017-03-16

Dinggang Shen , Guorong Wu , Heung‐Il Suk

This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and … This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

View PDF Chat

Machine Learning for Medical Imaging

2017-02-17

Bradley J. Erickson , Panagiotis Korfiatis , Zeynettin Akkus +1 more

Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can … Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. ©RSNA, 2017

View PDF Chat

A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology

2017-03-06

Neeraj Kumar , Ruchika Verma , Sanuj Sharma +3 more

Nuclear segmentation in digital microscopic tissue images can enable extraction of high-quality features for nuclear morphometrics and other analysis in computational pathology. Conventional image processing techniques, such as Otsu thresholding … Nuclear segmentation in digital microscopic tissue images can enable extraction of high-quality features for nuclear morphometrics and other analysis in computational pathology. Conventional image processing techniques, such as Otsu thresholding and watershed segmentation, do not work effectively on challenging cases, such as chromatin-sparse and crowded nuclei. In contrast, machine learning-based segmentation can generalize across various nuclear appearances. However, training machine learning algorithms requires data sets of images, in which a vast number of nuclei have been annotated. Publicly accessible and annotated data sets, along with widely agreed upon metrics to compare techniques, have catalyzed tremendous innovation and progress on other image classification problems, particularly in object recognition. Inspired by their success, we introduce a large publicly accessible data set of hematoxylin and eosin (H&E)-stained tissue images with more than 21000 painstakingly annotated nuclear boundaries, whose quality was validated by a medical doctor. Because our data set is taken from multiple hospitals and includes a diversity of nuclear appearances from several patients, disease states, and organs, techniques trained on it are likely to generalize well and work right out-of-the-box on other H&E-stained images. We also propose a new metric to evaluate nuclear segmentation results that penalizes object- and pixel-level errors in a unified manner, unlike previous metrics that penalize only one type of error. We also propose a segmentation technique based on deep learning that lays a special emphasis on identifying the nuclear boundaries, including those between the touching or overlapping nuclei, and works well on a diverse set of test images.

A survey on deep learning in medical image analysis

2017-07-26

Geert Litjens , Thijs Kooi , Babak Ehteshami Bejnordi +6 more

View PDF Chat

Deep Learning for Medical Image Processing: Overview, Challenges and the Future

2017-11-13

Imran Razzak , Saeeda Naz , Ahmad Zaib

View PDF Chat

Deep Learning in Medical Imaging: General Overview

2017-01-01

June‐Goo Lee , Sanghoon Jun , Young-Won Cho +4 more

The artificial neural network (ANN)-a machine learning technique inspired by the human neuronal synapse system-was introduced in the 1950s.However, the ANN was previously limited in its ability to solve actual … The artificial neural network (ANN)-a machine learning technique inspired by the human neuronal synapse system-was introduced in the 1950s.However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system.Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network.Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future.This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging.

View PDF Chat

Classification of breast cancer histology images using Convolutional Neural Networks

2017-06-01

Teresa Araújo , Guilherme Aresta , Eduardo Castro +5 more

Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on … Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

View PDF Chat

Overview of deep learning in medical imaging

2017-07-08

Kenji Suzuki

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

2018-09-06

Nicolas Coudray , Paolo Ocampo , Theodore Sakellaropoulos +6 more

View PDF Chat

Predicting cancer outcomes from histology and genomics using convolutional networks

2018-03-12

Pooya Mobadersany , Safoora Yousefi , Mohamed Amgad +5 more

Significance Predicting the expected outcome of patients diagnosed with cancer is a critical step in treatment. Advances in genomic and imaging technologies provide physicians with vast amounts of data, yet … Significance Predicting the expected outcome of patients diagnosed with cancer is a critical step in treatment. Advances in genomic and imaging technologies provide physicians with vast amounts of data, yet prognostication remains largely subjective, leading to suboptimal clinical management. We developed a computational approach based on deep learning to predict the overall survival of patients diagnosed with brain tumors from microscopic images of tissue biopsies and genomic biomarkers. This method uses adaptive feedback to simultaneously learn the visual patterns and molecular biomarkers associated with patient outcomes. Our approach surpasses the prognostic accuracy of human experts using the current clinical standard for classifying brain tumors and presents an innovative approach for objective, accurate, and integrated prediction of patient outcomes.

View PDF Chat

Deep Learning: A Primer for Radiologists

2017-11-01

Gabriel Chartrand , Phillip M. Cheng , Eugene Vorontsov +5 more

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. … Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. ©RSNA, 2017.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

2017-12-12

Babak Ehteshami Bejnordi , Mitko Veta , Paul Johannes van Diest +7 more

<h3>Importance</h3> Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. <h3>Objective</h3> Assess the performance of automated deep learning algorithms at detecting metastases in … <h3>Importance</h3> Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. <h3>Objective</h3> Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. <h3>Design, Setting, and Participants</h3> Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). <h3>Exposures</h3> Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. <h3>Main Outcomes and Measures</h3> The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. <h3>Results</h3> The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884];<i>P</i> < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). <h3>Conclusions and Relevance</h3> In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

View PDF Chat

Deep Learning Applications in Medical Image Analysis

2017-12-29

Justin Ker , Lipo Wang , Jai Prashanth Rao +1 more

The tremendous success of machine learning algorithms at image recognition tasks in recent years intersects with a time of dramatically increased use of electronic medical records and diagnostic imaging. This … The tremendous success of machine learning algorithms at image recognition tasks in recent years intersects with a time of dramatically increased use of electronic medical records and diagnostic imaging. This review introduces the machine learning algorithms as applied to medical image analysis, focusing on convolutional neural networks, and emphasizing clinical aspects of the field. The advantage of machine learning in an era of medical big data is that significant hierarchal relationships within the data can be discovered algorithmically without laborious hand-crafting of features. We cover key research areas and applications of medical image classification, localization, detection, segmentation, and registration. We conclude by discussing research obstacles, emerging trends, and possible future directions.

View PDF Chat

GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification

2018-09-21

Maayan Frid-Adar , Idit Diamant , Eyal Klang +3 more

View PDF Chat

Generative adversarial network in medical imaging: A review

2019-08-31

Yi Xin , Ekta Walia , Paul Babyn

View PDF Chat

MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation

2019-09-04

Nabil Ibtehaz , M. Sohel Rahman

View PDF Chat

Machine learning in medicine: a practical introduction

2019-03-19

Jenni A. M. Sidey-Gibbons , Chris Sidey‐Gibbons

Following visible successes on a wide range of predictive tasks, machine learning techniques are attracting substantial interest from medical researchers and clinicians. We address the need for capacity development in … Following visible successes on a wide range of predictive tasks, machine learning techniques are attracting substantial interest from medical researchers and clinicians. We address the need for capacity development in this area by providing a conceptual introduction to machine learning alongside a practical guide to developing and evaluating predictive algorithms using freely-available open source software and public domain data. We demonstrate the use of machine learning techniques by developing three predictive models for cancer diagnosis using descriptions of nuclei sampled from breast masses. These algorithms include regularized General Linear Model regression (GLMs), Support Vector Machines (SVMs) with a radial basis function kernel, and single-layer Artificial Neural Networks. The publicly-available dataset describing the breast mass samples (N=683) was randomly split into evaluation (n=456) and validation (n=227) samples. We trained algorithms on data from the evaluation sample before they were used to predict the diagnostic outcome in the validation dataset. We compared the predictions made on the validation datasets with the real-world diagnostic decisions to calculate the accuracy, sensitivity, and specificity of the three models. We explored the use of averaging and voting ensembles to improve predictive performance. We provide a step-by-step guide to developing algorithms using the open-source R statistical programming environment. The trained algorithms were able to classify cell nuclei with high accuracy (.94 -.96), sensitivity (.97 -.99), and specificity (.85 -.94). Maximum accuracy (.96) and area under the curve (.97) was achieved using the SVM algorithm. Prediction performance increased marginally (accuracy =.97, sensitivity =.99, specificity =.95) when algorithms were arranged into a voting ensemble. We use a straightforward example to demonstrate the theory and practice of machine learning for clinicians and medical researchers. The principals which we demonstrate here can be readily applied to other complex tasks including natural language processing and image recognition.

View PDF Chat

Digital pathology and artificial intelligence

2019-04-30

Muhammad Khalid Khan Niazi , Anil V. Parwani , Metin N. Gürcan

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

2019-05-29

Mohammad Hesam Hesamian , Wenjing Jia , Xiangjian He +1 more

Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical … Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

View PDF Chat

Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

2019-07-15

Gabriele Campanella , Matthew G. Hanna , Luke Geneslaw +7 more

Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology

2019-08-09

Kaustav Bera , Kurt A. Schalper , David L. Rimm +2 more

Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images

2019-09-18

Simon Graham , Quoc Dang Vu , Shan E Ahmed Raza +4 more

View PDF Chat

Dataset of breast ultrasound images

2019-11-21

Walid Al-Dhabyani , Mohammed Mohammed Mohammed Gomaa , Hussien Khaled +1 more

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of early deaths. The data presented in this article … Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of early deaths. The data presented in this article reviews the medical images of breast cancer using ultrasound scan. Breast Ultrasound Dataset is categorized into three classes: normal, benign, and malignant images. Breast ultrasound images can produce great results in classification, detection, and segmentation of breast cancer when combined with machine learning.

View PDF Chat

International evaluation of an AI system for breast cancer screening

2020-01-01

Scott Mayer McKinney , Marcin Sieniek , Varun Godbole +7 more

View PDF Chat

INbreast

2011-11-11

Inês Moreira , Igor Amaral , Inês Domingues +3 more

View PDF Chat

Medical Image Analysis using Convolutional Neural Networks: A Review

2018-10-08

Syed Muhammad Anwar , Muhammad Majid , Adnan Qayyum +3 more

View PDF Chat

Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support

2017-01-01

M. Jorge Cardoso , Tal Arbel , Gustavo Carneiro +7 more

View PDF Chat

Data-efficient and weakly supervised computational pathology on whole-slide images

2021-03-01

Ming Y. Lu , Drew F. K. Williamson , Tiffany Chen +3 more

View PDF Chat

Applications of Machine Learning in Cancer Prediction and Prognosis

2006-01-01

Joseph A. Cruz , David S. Wishart

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern … Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on “older” technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15–25%) improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression.

View PDF Chat

The evaluation of artificial intelligence in mammography-based breast cancer screening: Is breast-level analysis enough?

2025-06-25

Adnan Taib , George John William Partridge , L Yao +2 more | European Radiology

Abstract Objectives To assess whether the diagnostic performance of a commercial artificial intelligence (AI) algorithm for mammography differs between breast-level and lesion-level interpretations and to compare performance to a large … Abstract Objectives To assess whether the diagnostic performance of a commercial artificial intelligence (AI) algorithm for mammography differs between breast-level and lesion-level interpretations and to compare performance to a large population of specialised human readers. Materials and methods We retrospectively analysed 1200 mammograms from the NHS breast cancer screening programme using a commercial AI algorithm and assessments from 1258 trained human readers from the Personal Performance in Mammographic Screening (PERFORMS) external quality assurance programme. For breasts containing pathologically confirmed malignancies, a breast and lesion-level analysis was performed. The latter considered the locations of marked regions of interest for AI and humans. The highest score per lesion was recorded. For non-malignant breasts, a breast-level analysis recorded the highest score per breast. Area under the curve (AUC), sensitivity and specificity were calculated at the developer’s recommended threshold for recall. The study was designed to detect a medium-sized effect (odds ratio 3.5 or 0.29) for sensitivity. Results The test set contained 882 non-malignant (73%) and 318 malignant breasts (27%), with 328 cancer lesions. The AI AUC was 0.942 at breast level and 0.929 at lesion level (difference −0.013, p < 0.01). The mean human AUC was 0.878 at breast level and 0.851 at lesion level (difference −0.027, p < 0.01). AI outperformed human readers at the breast and lesion level ( ps < 0.01, respectively) according to the AUC. Conclusion AI’s diagnostic performance significantly decreased at the lesion level, indicating reduced accuracy in localising malignancies. However, its overall performance exceeded that of human readers. Key Points Question AI often recalls mammography cases not recalled by humans; to understand why, we as humans must consider the regions of interest it has marked as cancerous. Findings Evaluations of AI typically occur at the breast level, but performance decreases when AI is evaluated on a lesion level. This also occurs for humans. Clinical relevance To improve human-AI collaboration, AI should be assessed at the lesion level; poor accuracy here may lead to automation bias and unnecessary patient procedures. Graphical Abstract

Deep learning algorithms from histopathological images stratify molecular subtypes for leiomyosarcoma: a proof-and-concept diagnostic study

2025-06-25

Shaohui He , Jun Chen , Yan Fang Liu +7 more | International Journal of Surgery

Customized convolutional neural network with explainable AI for multimodal breast cancer detection

2025-06-25

Dipti Deb , Ratnakar Dash , Durga Prasad Mohapatra | Sadhana

Diagnostic Study of Head and Neck Metastatic Tumors From Different Primary Sites Based on Stacking Machine Learning Methods

2025-06-24

Yifei Liu , Cong Wu , Junpeng Ma +7 more | Journal of Biophotonics

ABSTRACT Metastatic tumors of the head and neck (MTHN) typically indicate advanced disease with a poor prognosis, originating from cells that spread from other body parts. Diagnosis generally relies on … ABSTRACT Metastatic tumors of the head and neck (MTHN) typically indicate advanced disease with a poor prognosis, originating from cells that spread from other body parts. Diagnosis generally relies on slow and error‐prone methods like imaging and histopathology. Addressing the need for a faster, more accurate diagnostic method, this study uses hyperspectral imaging to gather detailed cellular data from 208 patients at six primary MTHN sites. Techniques select characteristic spectral bands, and models including SVM, LightGBM, and ResNet are developed. A high‐performance classification model, MTHN‐SC, employs stacking technology with SVM and LightGBM as base learners and Random Forest as the meta‐learner, achieving a diagnostic accuracy of 82.47%, outperforming other models. This research enhances targeted treatment strategies and advances the application of hyperspectral technology in identifying MTHN primary sites.

MVT-Net: A novel cervical tumour segmentation using multi-view feature transfer learning

2025-06-24

Yao Yao , Yunzhi Chen , Yang An +4 more | PLoS ONE

Cervical cancer is one of the most aggressive malignant tumours of the reproductive system, posing a significant global threat to women's health. Accurately segmenting cervical tumours in MR images remains … Cervical cancer is one of the most aggressive malignant tumours of the reproductive system, posing a significant global threat to women's health. Accurately segmenting cervical tumours in MR images remains a challenging task due to the complex characteristics of tumours and the limitations of traditional methods. To address these challenges, this study proposes a novel cervical tumour segmentation model based on multi-view feature transfer learning, named MVT-Net. The model integrates a 2D global axial plane encoder-decoder network and a 3D multi-scale segmentation network as source and target domains, respectively. A transfer learning strategy is employed to extract diverse tumour-related information from multiple perspectives. In addition, a multi-scale residual blocks and a multi-scale residual attention blocks are embedded in the 3D network to effectively capture feature correlations across channels and spatial positions. Experiments on a cervical MR dataset of 160 images show that our proposed MVT-Net outperforms state-of-the-art methods, achieving a DICE score of [Formula: see text], an ASD of [Formula: see text] mm and superior performance in tumour localisation, shape delineation and edge segmentation. Ablation studies further validate the effectiveness of the proposed multi-view feature transfer strategy. These results demonstrate that our proposed MVT-Net represents a significant advance in cervical tumour segmentation, offering improved accuracy and reliability in clinical applications.

Multimodal Deep Learning Based on Ultrasound Images and Clinical Data for Better Ovarian Cancer Diagnosis

2025-06-24

Chang Su , Kuo Miao , Liwei Zhang +6 more | Deleted Journal

This study aimed to develop and validate a multimodal deep learning model that leverages 2D grayscale ultrasound (US) images alongside readily available clinical data to improve diagnostic performance for ovarian … This study aimed to develop and validate a multimodal deep learning model that leverages 2D grayscale ultrasound (US) images alongside readily available clinical data to improve diagnostic performance for ovarian cancer (OC). A retrospective analysis was conducted involving 1899 patients who underwent preoperative US examinations and subsequent surgeries for adnexal masses between 2019 and 2024. A multimodal deep learning model was constructed for OC diagnosis and extracting US morphological features from the images. The model's performance was evaluated using metrics such as receiver operating characteristic (ROC) curves, accuracy, and F1 score. The multimodal deep learning model exhibited superior performance compared to the image-only model, achieving areas under the curves (AUCs) of 0.9393 (95% CI 0.9139-0.9648) and 0.9317 (95% CI 0.9062-0.9573) in the internal and external test sets, respectively. The model significantly improved the AUCs for OC diagnosis by radiologists and enhanced inter-reader agreement. Regarding US morphological feature extraction, the model demonstrated robust performance, attaining accuracies of 86.34% and 85.62% in the internal and external test sets, respectively. Multimodal deep learning has the potential to enhance the diagnostic accuracy and consistency of radiologists in identifying OC. The model's effective feature extraction from ultrasound images underscores the capability of multimodal deep learning to automate the generation of structured ultrasound reports.

Validation of a Pretrained Artificial Intelligence Model for Pancreatic Cancer Detection on Diagnosis and Prediagnosis Computed Tomography Scans

2025-06-24

Liesbeth Degand , Clément Abi Nader , Alexandre Bône +6 more | Investigative Radiology

To evaluate PANCANAI, a previously developed AI model for pancreatic cancer (PC) detection, on a longitudinal cohort of patients. In particular, aiming for PC detection on scans acquired before histopathologic … To evaluate PANCANAI, a previously developed AI model for pancreatic cancer (PC) detection, on a longitudinal cohort of patients. In particular, aiming for PC detection on scans acquired before histopathologic diagnosis was assessed. The model has been previously trained to predict PC suspicion on 2134 portal venous CTs. In this study, the algorithm was evaluated on a retrospective cohort of Danish patients with biopsy-confirmed PC and with CT scans acquired between 2006 and 2016. The sensitivity was measured, and bootstrapping was performed to provide median and 95% CI. The study included 1083 PC patients (mean age: 69 y ± 11, 575 men). CT scans were divided into 2 groups: (1) concurrent diagnosis (CD): 1022 CT scans acquired within 2 months around histopathologic diagnosis, and (2) prediagnosis (PD): 198 CT scans acquired before histopathologic diagnosis (median 7 months before diagnosis). The sensitivity was 91.8% (938 of 1022; 95% CI: 89.9-93.5) and 68.7% (137 of 198; 95% CI: 62.1-75.3) on the CD and PD groups, respectively. Sensitivity on CT scans acquired 1 year or more before diagnosis was 53.9% (36 of 67; 95% CI: 41.8-65.7). Sensitivity on CT scans acquired at stage I was 82.9% (29 of 35; 95% CI: 68.6-94.3). PANCANAI showed high sensitivity for automatic PC detection on a large retrospective cohort of biopsy-confirmed patients. PC suspicion was detected in more than half of the CT scans that were acquired at least a year before histopathologic diagnosis.

Integrating Pretrained Deep Neural Networks with Traditional Classification Techniques for Enhanced Oral Cancer Diagnosis

2025-06-24

Bilal Şenol , Uğur Demiroğlu | Muş Alparslan Üniversitesi Fen Bilimleri Dergisi

The purpose of this research is to present a hybrid approach to the classification of oral cancer images. This approach combines traditional classification methods such as Support Vector Machines (SVM), … The purpose of this research is to present a hybrid approach to the classification of oral cancer images. This approach combines traditional classification methods such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Decision Trees with advanced feature extraction from pretrained deep neural networks (GoogleNet and MobileNetV2). Through the use of the suggested method, features are extracted from the deep learning models, resulting in the formation of a robust hybrid model that enhances diagnostic accuracy. The hybrid model achieves a classification accuracy of 90.01% with Quadratic SVM, which represents a 22.36% improvement over solo deep learning models. Comparative analyses indicate the tremendous performance advantages that the hybrid model has achieved. The findings highlight the potential of merging contemporary deep learning skills with older methods in order to improve the accuracy and dependability of medical picture categorization, particularly in the diagnostic process for oral cancer.

Digital Histopathology and <scp>AI</scp>: A New Era of Liver Fibrosis Quantification

2025-06-24

Luigi Terracciano , Luca Di Tommaso | Liver International

The Evolution of Cytopathology Reporting: Standardization, Precision, and Future Directions

2025-06-24

Fernando Schmitt | Journal of Clinical and Translational Pathology

Deep learning-based risk stratification of ductal carcinoma in situ using mammography and abbreviated breast magnetic resonance imaging

2025-06-24

Tingfeng Zhang , Tingting Cui , Zhenjie Cao +2 more | Frontiers in Oncology

Background Current management of ductal carcinoma in situ lacks robust risk stratification tools, leading to universal surgical and radiotherapy interventions despite heterogeneous progression risks. Optimizing therapeutic balance remains a critical … Background Current management of ductal carcinoma in situ lacks robust risk stratification tools, leading to universal surgical and radiotherapy interventions despite heterogeneous progression risks. Optimizing therapeutic balance remains a critical unmet clinical need. Materials and methods We retrospectively analyzed two patient cohorts. The first included 173 cases with BI-RADS category 3 or higher findings, used to compare the diagnostic accuracy of four abbreviated MRI protocols against the full diagnostic MRI. The second cohort involved 210 patients who had both mammography and abbreviated MRI. We developed two separate predictive models—one for pure ductal carcinoma in situ and another for invasive ductal carcinoma with associated ductal carcinoma in situ—by integrating clinical, imaging, and pathological features. Deep learning and natural language processing techniques were used to extract relevant features, and model performance was assessed using bootstrap validation. Results Abbreviated Magnetic Resonance Imaging protocols demonstrated similar diagnostic accuracy to the full protocol (P &gt; 0.05), offering a faster yet effective imaging option. The pure group incorporated features like nuclear grade, calcification morphology, and lesion size, achieving an Area Under the Curve of 0.905, with 86.8% accuracy and an F1 score of 0.853. The model for invasive cases incorporated features Ki-67 status, lymph vascular invasion, and enhancement patterns, achieved an Area Under the Curve of 0.880, with 86.2% accuracy and an F1 score of 0.834. Both models showed good calibration and clinical utility, as confirmed by bootstrap resampling and decision curve analysis. Conclusion Deep Learning-driven multimodal models enable precise ductal carcinoma in situ risk stratification, addressing overtreatment challenges. abbreviated Magnetic Resonance Imaging achieves diagnostic parity with full diagnostic protocol, positioning Magnetic Resonance Imaging as a viable ductal carcinoma in situ screening modality.

Binary Image Classification with ResNet

2025-06-24

Monica Maria Mihai , Tetyana O. Filimonova | Artificial Intelligence

The paper discusses the approach to binary image classification with ResNet based deep learning. Its actuality is the automatic image classification process and subject-the use of the methods of data … The paper discusses the approach to binary image classification with ResNet based deep learning. Its actuality is the automatic image classification process and subject-the use of the methods of data augmentation and in the improvement of the model accuracy-deep neural networks. The goal of this research was to develop and assess the efficiency of using the pre-trained ResNet network for solving the binary classification problem. Such image preprocessing and implementation for the augmentation method and mixed learning were conducted to optimize the classification process. The experimental results discussed point towards integration in preprocessing methods, dynamic image loading, and computational process optimization that drive substantial growth in the quality of classification, which carries great practical value in further explorations in this area

BREAST-CAD: A Computer-Aided Diagnosis System for Breast Cancer Detection Using Machine Learning

2025-06-24

Riyam M. Masoud , Ramadan Madi Ali Bakir , Mohamed S. Saraya +1 more | Technologies

This research presents a novel Computer-Aided Diagnosis (CAD) system called BREAST-CAD, developed to support clinicians in breast cancer detection. Our approach follows a three-phase methodology: Initially, a comprehensive literature review … This research presents a novel Computer-Aided Diagnosis (CAD) system called BREAST-CAD, developed to support clinicians in breast cancer detection. Our approach follows a three-phase methodology: Initially, a comprehensive literature review between 2000 and 2024 informed the choice of a suitable dataset and the selection of Naive Bayes (NB), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Decision Trees (DT) Machine Learning (ML) algorithms. Subsequently, the dataset was preprocessed and the four ML models were trained and validated, with the DT model achieving superior accuracy. We developed a novel, integrated client–server architecture for real-time diagnostic support, an aspect often underexplored in the current CAD literature. In the final phase, the DT model was embedded within a user-friendly client application, empowering clinicians to input patient diagnostic data directly and receive immediate, AI-driven predictions of cancer probability, with results securely transmitted and managed by a dedicated server, facilitating remote access and centralized data storage and ensuring data integrity.

Multimodal deep learning for predicting neoadjuvant treatment outcomes in breast cancer: a systematic review

2025-06-23

Eriseld Krasniqi , Lorena Filomeno , Teresa Arcuri +7 more | Biology Direct

Pathological complete response (pCR) to neoadjuvant systemic therapy (NAST) is an established prognostic marker in breast cancer (BC). Multimodal deep learning (DL), integrating diverse data sources (radiology, pathology, omics, clinical), … Pathological complete response (pCR) to neoadjuvant systemic therapy (NAST) is an established prognostic marker in breast cancer (BC). Multimodal deep learning (DL), integrating diverse data sources (radiology, pathology, omics, clinical), holds promise for improving pCR prediction accuracy. This systematic review synthesizes evidence on multimodal DL for pCR prediction and compares its performance against unimodal DL. Following PRISMA, we searched PubMed, Embase, and Web of Science (January 2015-April 2025) for studies applying DL to predict pCR in BC patients receiving NAST, using data from radiology, digital pathology (DP), multi-omics, and/or clinical records, and reporting AUC. Data on study design, DL architectures, and performance (AUC) were extracted. A narrative synthesis was conducted due to heterogeneity. Fifty-one studies, mostly retrospective (90.2%, median cohort 281), were included. Magnetic resonance imaging and DP were common primary modalities. Multimodal approaches were used in 52.9% of studies, often combining imaging with clinical data. Convolutional neural networks were the dominant architecture (88.2%). Longitudinal imaging improved prediction over baseline-only (median AUC 0.91 vs. 0.82). Overall, the median AUC across studies was 0.88, with 35.3% achieving AUC ≥ 0.90. Multimodal models showed a modest but consistent improvement over unimodal approaches (median AUC 0.88 vs. 0.83). Omics and clinical text were rarely primary DL inputs. DL models demonstrate promising accuracy for pCR prediction, especially when integrating multiple modalities and longitudinal imaging. However, significant methodological heterogeneity, reliance on retrospective data, and limited external validation hinder clinical translation. Future research should prioritize prospective validation, integration underutilized data (multi-omics, clinical), and explainable AI to advance DL predictors to the clinical setting.

A stacking ensemble method with multiple color models for lung cancer classification using histopathology images

2025-06-23

Manish Hazra , Nandita Gautam , J. Dey +1 more | Multimedia Tools and Applications

Multi-view co-occurrence and dual-modality framework for breast cancer classification

2025-06-23

Chong Su , Zhenghua Gong , Jie Cao | Journal of King Saud University - Computer and Information Sciences

APPLICATION OF MACHINE LEARNING FOR BREAST CANCER DIAGNOSIS: A RANDOM FOREST-BASED APPROACH

2025-06-23

João Victor Rodrigues da Silva , Laura Naomi Funck Ougui , Beatriz Santos de Araújo +3 more | Journal of Media Critiques

Breast cancer is one of the leading causes of morbidity and mortality among women worldwide. Early and accurate diagnosis is essential to increase the chances of successful treatment and patient … Breast cancer is one of the leading causes of morbidity and mortality among women worldwide. Early and accurate diagnosis is essential to increase the chances of successful treatment and patient survival. In this context, machine learning has emerged as a powerful tool for medical diagnosis, particularly in oncology. This study aims to develop a breast tumor classification model using the Random Forest algorithm, based on clinical and physical features from the Wisconsin Breast Cancer Dataset. The methodology involved data cleaning, normalization, and division into training and test sets. The Random Forest model was trained with 100 decision trees and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The results showed an accuracy of 96.5%, with precision and recall values of 0.98 and 0.93, respectively, for malignant tumors, and an F1-score of 0.95. These results indicate a high capacity of the model to correctly classify breast tumors, especially in detecting malignancies. Additionally, the analysis of the most influential features—such as radius, perimeter, and texture—highlighted their potential as biomarkers for early diagnosis. This research demonstrates that Random Forest can significantly contribute to improving diagnostic accuracy in breast cancer and may be a valuable tool in clinical practice.

Prediction of Cervical Cancer with Machine Learning Approaches

2025-06-22

Aditya S. Pandey , Jatin Arora , G. S. Kohli +3 more | Journal of The Institution of Engineers (India) Series B

Upgrade Rate and Associated Predictive Factors of Papillary Breast Lesions on Core Needle Biopsy in a Private Tertiary Institution:

2025-06-21

Manuelito Madrid , Natasha Vitória Teixeira Santos | Philippine Journal of Pathology

Objective. The aim of this study was to determine the upgrade rate in diagnosis of biopsy-proven papillary breast lesions on core needle biopsy and their respective surgical excisions, and to … Objective. The aim of this study was to determine the upgrade rate in diagnosis of biopsy-proven papillary breast lesions on core needle biopsy and their respective surgical excisions, and to assess for predictive factors associated with an upgrade at St. Luke’s Medical Center – Global City. Methodology. A retrospective review of our institution’s database identified 184 papillary breast lesions diagnosed by core needle biopsy. The study population consisted of 71 samples that met the inclusion criteria. The overall upgrade and concordance rates were determined and analyzed if there was any significant association with clinical demographics, radiologic findings, and core diameter on gross examination. Continuous variables were presented as mean and median, and Shapiro-Wilk test was used to assess normality of data. Categorical variables were expressed as frequencies and percentages. Simple logistic regression analysis with Firth’s bias correction was performed to determine the variables associated with a diagnostic upgrade. P values ≤0.05 were considered statistically significant. Results. A total 71 patients, all female, were included in the study. The overall upgrade rate was 8.45% (95% CI: 3.16-17.49%) in comparison with the diagnosis of the initial CNB and SE alone. This translated to 6/71 samples in this study. The overall concordance was 91.55% based on clinical significance, and an individual diagnosis concordance rate of 78.87%. None of the predictive factors (i.e., age, history of breast cancer, BI-RADS score, and gross core diameter) assessed showed an association with a diagnostic upgrade. Conclusion. The computed overall upgrade rate is within range of currently published literature. The concordance rates for both clinical significance and individual diagnosis were quite high, suggesting good reproducibility of histopathologic diagnosis within our institution. This was also found to be consistent with other studies. Of the predictive factors, none showed an association to a diagnostic upgrade. Despite the latter, our findings may be of value within the medical center in further exploring and expanding the data set at hand, such that it may hopefully contribute to local guidelines in managing PBLs in the future.

Assessment of the efficacy and accuracy of cervical cytology screening with the Hologic Genius Digital Diagnostics System

2025-06-21

Esther Elishaev , Lakshmi Harinath , Yuhong Ye +7 more | Cancer Cytopathology

Abstract Background Medical technologies powered by artificial intelligence are quickly transforming into practical solutions by rapidly leveraging massive amounts of data processed via deep learning algorithms. There is a necessity … Abstract Background Medical technologies powered by artificial intelligence are quickly transforming into practical solutions by rapidly leveraging massive amounts of data processed via deep learning algorithms. There is a necessity to validate these innovative tools when integrated into clinical practice. Methods This study evaluated the performance of the Hologic Genius Digital Diagnostics System (HGDDS) with a cohort of 890 previously reviewed and diagnosed ThinPrep Papanicolaou (Pap) tests with the intent to deploy this system for routine clinical use. The study included all diagnostic categories of The Bethesda System, with follow‐up tissue sampling performed within 6 months of abnormal Pap test results to serve as the ground truth. Results The HGDDS demonstrated excellent performance in detecting significant Pap test findings, with close to 100% sensitivity (98.2%–100%) for cases classified as atypical squamous cells of undetermined significance and above within a 95% confidence interval and a high negative predictive value (92.4%–100%). Conclusions The HGDDS streamlined workflow, reduced manual workload, and functioned as a stand‐alone system.

Decoupling mean teacher via Dual students: a prototype-based framework for semi-supervised medical segmentation

2025-06-20

Zuo Yang , Renfeng Zhang , Xiurui Guo +2 more | Complex & Intelligent Systems

MVKD-Trans: A Multi-View Knowledge Distillation Vision Transformer Architecture for Breast Cancer Classification Based on Ultrasound Images

2025-06-20

David Ngo Chek Ling , Xiong Jiao | Ultrasonic Imaging

Breast cancer is the leading cancer threatening women’s health. In recent years, deep neural networks have outperformed traditional methods in terms of both accuracy and efficiency for breast cancer classification. … Breast cancer is the leading cancer threatening women’s health. In recent years, deep neural networks have outperformed traditional methods in terms of both accuracy and efficiency for breast cancer classification. However, most ultrasound-based breast cancer classification methods rely on single-perspective information, which may lead to higher misdiagnosis rates. In this study, we propose a multi-view knowledge distillation vision transformer architecture (MVKD-Trans) for the classification of benign and malignant breast tumors. We utilize multi-view ultrasound images of the same tumor to capture diverse features. Additionally, we employ a shuffle module for feature fusion, extracting channel and spatial dual-attention information to improve the model’s representational capability. Given the limited computational capacity of ultrasound devices, we also utilize knowledge distillation (KD) techniques to compress the multi-view network into a single-view network. The results show that the accuracy, area under the ROC curve (AUC), sensitivity, specificity, precision, and F1 score of the model are 88.15%, 91.23%, 81.41%, 90.73%, 78.29%, and 79.69%, respectively. The superior performance of our approach, compared to several existing models, highlights its potential to significantly enhance the understanding and classification of breast cancer.

Artificial intelligence-based tumor size measurement on mammography: agreement with pathology and comparison with human readers’ assessments across multiple imaging modalities

2025-06-20

Mi-ri Kwon , Sung Hun Kim , Ga Eun Park +4 more | La radiologia medica

Efficient and Lightweight Block-Based Feature Selection Approach Using Dice Coefficient with Machine Learning for Accurate Breast Cancer Classification

2025-06-20

| International journal of intelligent engineering and systems

Comparative Evaluation of Support Vector Classifier, Random Forest, and XGBoost for Early Breast Cancer Prediction With Feature Importance and Class Balancing

2025-06-19

Deepti Sharda , Ritika Bansal , Prachi Gumber +2 more | Cureus Journal of Computer Science.

Optimized YOLOv8 for enhanced breast tumor segmentation in ultrasound imaging

2025-06-19

Ayman Mohamed Mostafa , Alaa Alaerjan , Bader Aldughayfiq +5 more | Discover Oncology

An Exploration of Discrepant Recalls Between AI and Human Readers of Malignant Lesions in Digital Mammography Screening

2025-06-19

Suzanne L. van Winkel , Ioannis Sechopoulos , Alejandro Rodríguez‐Ruiz +7 more | Diagnostics

Background: The integration of artificial intelligence (AI) in digital mammography (DM) screening holds promise for early breast cancer detection, potentially enhancing accuracy and efficiency. However, AI performance is not identical … Background: The integration of artificial intelligence (AI) in digital mammography (DM) screening holds promise for early breast cancer detection, potentially enhancing accuracy and efficiency. However, AI performance is not identical to that of human observers. We aimed to identify common morphological image characteristics of true cancers that are missed by either AI or human screening when their interpretations are discrepant. Methods: Twenty-six breast cancer-positive cases, identified from a large retrospective multi-institutional digital mammography dataset based on discrepant AI and human interpretations, were included in a reader study. Ground truth was confirmed by histopathology or ≥1-year follow-up. Fourteen radiologists assessed lesion visibility, morphological features, and likelihood of malignancy. AI performance was evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC). The reader study results were analyzed using interobserver agreement measures and descriptive statistics. Results: AI demonstrated high discriminative capability in the full dataset, with AUCs ranging from 0.903 (95% CI: 0.862-0.944) to 0.946 (95% CI: 0.896-0.996). Cancers missed by AI had a significantly smaller median size (9.0 mm, IQR 6.5-12.0) compared to those missed by human readers (21.0 mm, IQR 10.5-41.0) (p = 0.0014). Cancers in discrepant cases were often described as having 'low visibility', 'indistinct margins', or 'irregular shape'. Calcifications were observed in 27% of human-missed cancers (42/154) versus 18% of AI-missed cancers (38/210). A very high likelihood of malignancy was assigned in 32.5% (50/154) of human-missed cancers compared to 19.5% (41/210) of AI-missed cancers. Overall inter-rater agreement was poor to fair (<0.40), indicating interpretation challenges of the selected images. Among the human-missed cancers, calcifications were more frequent (42/154; 27%) than among the AI-missed cancers (38/210; 18%) (p = 0.396). Furthermore, 50/154 (32.5%) human-missed cancers were deemed to have a very high likelihood of malignancy, compared to 41/210 (19.5%) AI-missed cancers (p = 0.8). Overall inter-rater agreement on the items assessed during the reader study was poor to fair (<0.40), suggesting that interpretation of the selected images was challenging. Conclusions: Lesions missed by AI were smaller and less often calcified than cancers missed by human readers. Cancers missed by AI tended to show lower levels of suspicion than those missed by human readers. While definitive conclusions are premature, the findings highlight the complementary roles of AI and human readers in mammographic interpretation.

A Hybrid Deep Learning Framework for Accurate Cell Segmentation in Whole Slide Images Using YOLOv11, StarDist, and SAM2

2025-06-19

Julius Bamwenda , Mehmet Siraç Özerdem , Orhan Ayyıldız +1 more | Bioengineering

Accurate segmentation of cellular structures in whole slide images (WSIs) is essential for quantitative analysis in computational pathology. However, the complexity and scale of WSIs present significant challenges for conventional … Accurate segmentation of cellular structures in whole slide images (WSIs) is essential for quantitative analysis in computational pathology. However, the complexity and scale of WSIs present significant challenges for conventional segmentation methods. In this study, we propose a novel hybrid deep learning framework that integrates three complementary approaches, YOLOv11, StarDist, and Segment Anything Model v2 (SAM2), to achieve robust and precise cell segmentation. The proposed pipeline utilizes YOLOv11 as an object detector to localize regions of interest, generating bounding boxes or preliminary masks that are subsequently used either as prompts to guide SAM2 or to filter segmentation outputs. StarDist is employed to model cell and nuclear boundaries with high geometric precision using star-convex polygon representations, which are particularly effective in densely packed cellular regions. The framework was evaluated on a unique WSI dataset comprising 256 × 256 image tiles annotated with high-resolution cell-level masks. Quantitative evaluations using the Dice coefficient, intersection over union (IoU), F1-score, precision, and recall demonstrated that the proposed method significantly outperformed individual baseline models. The integration of object detection and prompt-based segmentation led to enhanced boundary accuracy, improved localization, and greater robustness across varied tissue types. This work contributes a scalable and modular solution for advancing automated histopathological image analysis.

AN INTELLECTUAL DEEP LEARNING STRATEGY FOR BREAST CANCER DIAGNOSIS USING 3D TRANS-RESUNET3+ ASSISTED SEGMENTATION MECHANISM

2025-06-19

Thippaluru Umamaheswari , Y. Murali Mohanbabu | Biomedical Engineering Applications Basis and Communications

Globally, breast cancer is a deadly disease for women. Early detection of breast cancer helps control and avoids high risk. The mammogram imaging approach is used to screen and detect … Globally, breast cancer is a deadly disease for women. Early detection of breast cancer helps control and avoids high risk. The mammogram imaging approach is used to screen and detect abnormalities and assess their precise location. Better-quality mammogram images are highly required to detect and enhance the patient’s prognosis of breast cancer in an earlier stage. The traditional technique for breast screening considers X-ray images for the early detection of tumors. In dense breasts, the sensitivity analysis for breast cancer detection is generally a low value of 0.8261. Furthermore, it suffers from problems when screening the images to detect small abnormalities. Enhanced deep learning is an improved version of a machine learning mechanism that demands a higher computation power. Thus, this research focuses on designing an adaptive deep-learning model to identify tumor locations for better diagnosis. The required mammogram images are collected through standard data sources and fed to the segmentation mechanism to detect the exact location of cancerous tissue. Here, the Three-Dimensional Trans-ResUnet3[Formula: see text] (3DTRUnet3[Formula: see text] model is utilized for the effective abnormal region segmentation. The segmented images are fed into the classification network named Attention-based Adaptive ShufflenetV2 with Long Short-Term Memory (AASv2-LSTM) for diagnosing breast cancer. Hence, the tumor diagnosis is effectively done using the Best and Worst Fitness-aided Golf Optimization (BWF-GO) to improve classification performance. The diagnosis performance of the implemented task is validated with classical models concerning various measures. Throughout the entire experimental validation, the developed model obtains 96.92% accuracy which ensures the system’s effectiveness. This evaluation helps to provide a better diagnosis process that certainly improves the chance of survival and reduces the risk of mortality rate.

Design of a novel fuzzy ensemble CNN framework for ovarian cancer classification using tissue microarray images

2025-06-19

Tat-Bao-Thien Nguyen , Anh T. Vu-Xuan , Vuong M. Ngo | Image and Vision Computing

STN-DRN: Integrating Spatial Transformer Network with Deep Residual Network for Multiclass Classification of Alzheimer's Disease

2025-06-19

Prabu Selvam , S Sudharson , P. N. Senthil Prakash | CRC Press eBooks

Leveraging advanced feature extraction for improved kidney biopsy segmentation

2025-06-18

Muhammad Wajeeh Us Sima , Chengliang Wang , Muhammad Arshad +3 more | Frontiers in Medicine

Medical image segmentation faces critical challenges in renal histopathology due to the intricate morphology of glomeruli characterized by small size, fragmented structures, and low contrast against complex tissue backgrounds. While … Medical image segmentation faces critical challenges in renal histopathology due to the intricate morphology of glomeruli characterized by small size, fragmented structures, and low contrast against complex tissue backgrounds. While the Segment Anything Model (SAM) excels in natural image segmentation, its direct application to medical imaging underperforms due to (1) insufficient preservation of fine-grained anatomical details, (2) computational inefficiency on gigapixel whole-slide images (WSIs), and (3) poor adaptation to domain-specific features like staining variability and sparse annotations. To address these limitations, we propose V-SAM, a novel framework enhancing SAM's architecture through three key innovations: (1) a V-shaped adapter that preserves spatial hierarchies via multi-scale skip connections, recovering capillary-level details lost in SAM's aggressive downsampling; (2) lightweight adapter layers that fine-tune SAM's frozen encoder with fewer trainable parameters, optimizing it for histopathology textures while avoiding catastrophic forgetting; and (3) a dynamic point-prompt mechanism enabling sub-pixel refinement of glomerular boundaries through gradient aware localization. Evaluated on the HuBMAP Hacking the Human Vasculature and Hacking the Kidney datasets, V-SAM achieves state-of-the-art performance, surpassing 89.31%, 97.65% accuracy, 86.17%, 95.54% F1-score respectively. V-SAM sets a new paradigm for adapting foundation models to clinical workflows, with direct applications in chronic kidney disease diagnosis and biomarker discovery. This work bridges the gap between SAM's generalizability and the precision demands of medical imaging, offering a scalable solution for resource constrained healthcare environments.

Enhancing AI-Driven Diagnosis of Invasive Ductal Carcinoma with Morphologically Guided and Interpretable Deep Learning

2025-06-18

Suphakon Jarujunawong , Paramate Horkaew | Applied Sciences

Artificial intelligence is increasingly shaping the landscape of computer-aided diagnosis of breast cancer. Despite incrementally improved accuracy, pathologist supervision remains essential for verified interpretation. While prior research focused on devising … Artificial intelligence is increasingly shaping the landscape of computer-aided diagnosis of breast cancer. Despite incrementally improved accuracy, pathologist supervision remains essential for verified interpretation. While prior research focused on devising deep model architecture, this study examines the pivotal role of multi-band visual-enhanced features in invasive ductal carcinoma classification using whole slide imaging. Our results showed that orientation invariant filters achieved an accuracy of 0.8125, F1-score of 0.8134, and AUC of 0.8761, while preserving cellular arrangement and tissue morphology. By utilizing spatial relationships across varying extents, the proposed fusion strategy aligns with pathological interpretation principles. While integrating Gabor wavelet responses into ResNet-50 enhanced feature association, the comparative analysis emphasized the benefits of weighted morphological fusion, further strengthening diagnostic performance. These insights underscore the crucial role of informative filters in advancing DL schemes for breast cancer screening. Future research incorporating diverse, multi-center datasets could further validate the approach and broaden its diagnostic applications.

HMA-Net: a hybrid mixer framework with multihead attention for breast ultrasound image segmentation

2025-06-18

Soumya Sara Koshy , L. Jani Anbarasi | Frontiers in Artificial Intelligence

Introduction Breast cancer is a severe illness predominantly affecting women, and in most cases, it leads to loss of life if left undetected. Early detection can significantly reduce the mortality … Introduction Breast cancer is a severe illness predominantly affecting women, and in most cases, it leads to loss of life if left undetected. Early detection can significantly reduce the mortality rate associated with breast cancer. Ultrasound imaging has been widely used for effectively detecting the disease, and segmenting breast ultrasound images aid in the identification and localization of tumors, thereby enhancing disease detection accuracy. Numerous computer-aided methods have been proposed for the segmentation of breast ultrasound images. Methods A deep learning-based architecture utilizing a ConvMixer-based encoder and ConvNeXT-based decoder coupled with convolution-enhanced multihead attention has been proposed for segmenting breast ultrasound images. The enhanced ConvMixer modules utilize spatial filtering and channel-wise integration to efficiently capture local and global contextual features, enhancing feature relevance and thus increasing segmentation accuracy through dynamic channel recalibration and residual connections. The bottleneck with the attention mechanism enhances segmentation by utilizing multihead attention to capture long-range dependencies, thus enabling the model to focus on relevant features across distinct regions. The enhanced ConvNeXT modules with squeeze and excitation utilize depthwise convolution for efficient spatial filtering, layer normalization for stabilizing training, and residual connections to ensure the preservation of relevant features for accurate segmentation. A combined loss function, integrating binary cross entropy and dice loss, is used to train the model. Results The proposed model has an exceptional performance in segmenting intricate structures, as confirmed by comprehensive experiments conducted on two datasets, namely the breast ultrasound image dataset (BUSI) dataset and the BrEaST dataset of breast ultrasound images. The model achieved a Jaccard index of 98.04% and 94.84% and a Dice similarity coefficient of 99.01% and 97.35% on the BUSI and BrEaST datasets, respectively. Discussion The ConvMixer and ConvNeXT modules are integrated with convolution-enhanced multihead attention, which enhances the model's ability to capture local and global contextual information. The strong performance of the model on the BUSI and BrEaST datasets demonstrates the robustness and generalization capability of the model.

Applying a multi-task and multi-instance framework to predict axillary lymph node metastases in breast cancer

2025-06-18

Yi‐Zhi Li , Zonglin Chen , Ziyuan Ding +7 more | npj Precision Oncology

Abstract Deep learning (DL) models have shown promise in predicting axillary lymph node (ALN) status. However, most existing DL models were classification-only models and did not consider the practical application … Abstract Deep learning (DL) models have shown promise in predicting axillary lymph node (ALN) status. However, most existing DL models were classification-only models and did not consider the practical application scenarios of multi-view joint prediction. Here, we propose a Multi-Task Learning (MTL) and Multi-Instance Learning (MIL) framework that simulates the real-world clinical diagnostic scenario for ALN status prediction in breast cancer. Ultrasound images of the primary tumor and ALN (if available) regions were collected, each annotated with a segmentation label. The model was trained on a training cohort and tested on both internal and external test cohorts. The proposed two-stage DL framework using one of the Transformer models, Segformer, as the network backbone, exhibits the top-performing model. It achieved an AUC of 0.832, a sensitivity of 0.815, and a specificity of 0.854 in the internal test cohort. In the external cohort, this model attained an AUC of 0.918, a sensitivity of 0.851 and a specificity of 0.957. The Class Activation Mapping method demonstrated that the DL model correctly identified the characteristic areas of metastasis within the primary tumor and ALN regions. This framework may serve as an effective second reader to assist clinicians in ALN status assessment.

Advancing breast cancer prediction: Comparative analysis of ML models and deep learning-based multi-model ensembles on original and synthetic datasets

2025-06-18

Kazi Arman Ahmed , Israt Humaira , Ashiqur Rahman Khan +7 more | PLoS ONE

Breast cancer is a significant global health concern with rising incidence and mortality rates. Current diagnostic methods face challenges, necessitating improved approaches. This study employs various machine learning (ML) algorithms, … Breast cancer is a significant global health concern with rising incidence and mortality rates. Current diagnostic methods face challenges, necessitating improved approaches. This study employs various machine learning (ML) algorithms, including KNN, SVM, ANN, RF, XGBoost, ensemble models, AutoML, and deep learning (DL) techniques, to enhance breast cancer diagnosis. The objective is to compare the efficiency and accuracy of these models using original and synthetic datasets, contributing to the advancement of breast cancer diagnosis. The methodology comprises three phases, each with two stages. In the first stage of each phase, stratified K-fold cross-validation was performed to train and evaluate multiple ML models. The second stage involved DL-based and AutoML-based ensemble strategies to improve prediction accuracy. In the second and third phases, synthetic data generation methods, such as Gaussian Copula and TVAE, were utilized. The KNN model outperformed others on the original dataset, while the AutoML approach using H2OXGBoost using synthetic data also showed high accuracy. These findings underscore the effectiveness of traditional ML models and AutoML in predicting breast cancer. Additionally, the study demonstrated the potential of synthetic data generation methods to improve prediction performance, aiding decision-making in the diagnosis and treatment of breast cancer.

Exploring the evolution of artificial intelligence in pathology: a bibliometric and network analysis

2025-06-18

Burcu Sanal Yılmaz | Journal of Medicine and Palliative Care

Aims: Artificial intelligence (AI) has emerged as a transformative force in pathology, significantly influencing diagnostic accuracy, workflow efficiency, and digital pathology integration. Despite the rapid growth in AI-related pathology research, … Aims: Artificial intelligence (AI) has emerged as a transformative force in pathology, significantly influencing diagnostic accuracy, workflow efficiency, and digital pathology integration. Despite the rapid growth in AI-related pathology research, a comprehensive analysis of publication trends, key contributors, and scientific impact remains limited. This study aims to provide a bibliometric and network analysis of AI applications in pathology, mapping research trends, citation networks, institutional collaborations, and emerging thematic clusters. Methods: A bibliometric analysis was conducted using data from the Web of Science Core Collection, covering studies published between 2007 and 2024. Research trends, citation distributions, keyword co-occurrences, and collaboration networks were analyzed using VOSviewer. Descriptive statistics and network visualization techniques were applied to assess publication growth, author collaborations, and journal impact. Results: The findings are consistent with other studies showing a more than proportionate increase in AI-based research in pathology since 2018, especially AI related pathology research is on a significant rise focusing on laboratory investigation, modern pathology and journal of pathology as the primary high impact journals. Important research centers like the University of Pittsburgh, Radboud Universiteit, and the Cleveland Clinic have made significant advancements in AI based pathology which have and will continue to make a significant impact within this area. The key words used most frequently were “AI”, “digital pathology”, “deep learning”, and “machine learning” which corroborate the centrality of AI in pathology. Conclusion: AI does have a major contribution towards transforming pathology by aiding in providing quick and efficient diagnosis. Nonetheless, issues around the standardization of data, the black box nature of algorithms, and the regulation of data raise serious challenges towards achieving successful clinical incorporation of AI. The focus of future work should center around standardization of validation protocols, inter-disciplinarity, and ethical issues in order to ensure the dependable implementation of AI enabled solutions in pathology.

Interactive prototype learning and self-learning for few-shot medical image segmentation

2025-06-18

Yuhui Song , Chenchu Xu , Boyan Wang +4 more | Artificial Intelligence in Medicine