Dynamic model scaling based on segmented tumor size for breast cancer detection

<p>The accuracy of breast cancer detection in histopathology images presents a critical challenge and remains a central focus in advancements in computational pathology. Scaling Convolutional Neural Networks (CNNs) can improve feature extraction, especially in multi-class problems that require...

Full description

Saved in:
Bibliographic Details
Main Author: Younes Akbari (16303286) (author)
Other Authors: Faseela Abdullakutty (22564814) (author), Somaya Al-Maadeed (5178131) (author), Ahmed Bouridane (2270131) (author), Rifat Hamoudi (523339) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513532723200000
author Younes Akbari (16303286)
author2 Faseela Abdullakutty (22564814)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Hamoudi (523339)
author2_role author
author
author
author
author_facet Younes Akbari (16303286)
Faseela Abdullakutty (22564814)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Hamoudi (523339)
author_role author
dc.creator.none.fl_str_mv Younes Akbari (16303286)
Faseela Abdullakutty (22564814)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Hamoudi (523339)
dc.date.none.fl_str_mv 2025-11-06T12:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.bspc.2025.109118
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Dynamic_model_scaling_based_on_segmented_tumor_size_for_breast_cancer_detection/30636260
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Histopathology image
Breast cancer image segmentation and classification
Model scaling
Conditional diffusion probabilistic model
dc.title.none.fl_str_mv Dynamic model scaling based on segmented tumor size for breast cancer detection
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>The accuracy of breast cancer detection in histopathology images presents a critical challenge and remains a central focus in advancements in computational pathology. Scaling Convolutional Neural Networks (CNNs) can improve feature extraction, especially in multi-class problems that require varying levels of complexity to distinguish between different classes. However, selecting the optimal model complexity for each image remains a persistent challenge. Current approaches predominantly rely on fixed-complexity models regardless of individual image characteristics. This study introduces an adaptive method that intelligently matches model complexity to tumor characteristics by integrating a Denoising Diffusion Probabilistic Model (DDPM), a generative model that iteratively improves segmentation accuracy by progressively removing noise, for tumor region segmentation with a range of EfficientNet architectures for classification. The segmentation model, trained on a specialized dataset of breast cancer regions, identifies tumor regions in testing images from breast cancer detection datasets. Based on the size of the segmented tumor region, an appropriate EfficientNet model, ranging from B0 to B7, is dynamically selected for classification. The core insight is that smaller or undetected tumor regions require less computational complexity and can be accurately classified using efficient models like EfficientNet-B0, while larger tumor regions benefit from the enhanced feature extraction capabilities of deeper models like EfficientNet-B7 to capture more intricate features. This adaptive approach mitigates segmentation inaccuracies and ensures that the appropriate model complexity is applied based on tumor characteristics. Rigorously evaluated on three distinct datasets, the proposed approach demonstrates superior performance compared to leading techniques, particularly in terms of 95% confidence intervals, the area under the precision–recall curve (PR-AUC), and accuracy, achieving 93.86% accuracy with 95% confidence intervals of [93.15–95.31%] and PR-AUC of 0.986 on the BRACS dataset. This approach represents a notable advancement in breast cancer detection within histopathology images and holds significant potential as a tool in computational pathology.</p><h2>Other Information</h2> <p> Published in: Biomedical Signal Processing and Control<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.bspc.2025.109118" target="_blank">https://dx.doi.org/10.1016/j.bspc.2025.109118</a></p>
eu_rights_str_mv openAccess
id Manara2_ffb82e794e8396dcb1b4381c5e433b6d
identifier_str_mv 10.1016/j.bspc.2025.109118
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30636260
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Dynamic model scaling based on segmented tumor size for breast cancer detectionYounes Akbari (16303286)Faseela Abdullakutty (22564814)Somaya Al-Maadeed (5178131)Ahmed Bouridane (2270131)Rifat Hamoudi (523339)Biomedical and clinical sciencesOncology and carcinogenesisHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceMachine learningHistopathology imageBreast cancer image segmentation and classificationModel scalingConditional diffusion probabilistic model<p>The accuracy of breast cancer detection in histopathology images presents a critical challenge and remains a central focus in advancements in computational pathology. Scaling Convolutional Neural Networks (CNNs) can improve feature extraction, especially in multi-class problems that require varying levels of complexity to distinguish between different classes. However, selecting the optimal model complexity for each image remains a persistent challenge. Current approaches predominantly rely on fixed-complexity models regardless of individual image characteristics. This study introduces an adaptive method that intelligently matches model complexity to tumor characteristics by integrating a Denoising Diffusion Probabilistic Model (DDPM), a generative model that iteratively improves segmentation accuracy by progressively removing noise, for tumor region segmentation with a range of EfficientNet architectures for classification. The segmentation model, trained on a specialized dataset of breast cancer regions, identifies tumor regions in testing images from breast cancer detection datasets. Based on the size of the segmented tumor region, an appropriate EfficientNet model, ranging from B0 to B7, is dynamically selected for classification. The core insight is that smaller or undetected tumor regions require less computational complexity and can be accurately classified using efficient models like EfficientNet-B0, while larger tumor regions benefit from the enhanced feature extraction capabilities of deeper models like EfficientNet-B7 to capture more intricate features. This adaptive approach mitigates segmentation inaccuracies and ensures that the appropriate model complexity is applied based on tumor characteristics. Rigorously evaluated on three distinct datasets, the proposed approach demonstrates superior performance compared to leading techniques, particularly in terms of 95% confidence intervals, the area under the precision–recall curve (PR-AUC), and accuracy, achieving 93.86% accuracy with 95% confidence intervals of [93.15–95.31%] and PR-AUC of 0.986 on the BRACS dataset. This approach represents a notable advancement in breast cancer detection within histopathology images and holds significant potential as a tool in computational pathology.</p><h2>Other Information</h2> <p> Published in: Biomedical Signal Processing and Control<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.bspc.2025.109118" target="_blank">https://dx.doi.org/10.1016/j.bspc.2025.109118</a></p>2025-11-06T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.bspc.2025.109118https://figshare.com/articles/journal_contribution/Dynamic_model_scaling_based_on_segmented_tumor_size_for_breast_cancer_detection/30636260CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306362602025-11-06T12:00:00Z
spellingShingle Dynamic model scaling based on segmented tumor size for breast cancer detection
Younes Akbari (16303286)
Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Histopathology image
Breast cancer image segmentation and classification
Model scaling
Conditional diffusion probabilistic model
status_str publishedVersion
title Dynamic model scaling based on segmented tumor size for breast cancer detection
title_full Dynamic model scaling based on segmented tumor size for breast cancer detection
title_fullStr Dynamic model scaling based on segmented tumor size for breast cancer detection
title_full_unstemmed Dynamic model scaling based on segmented tumor size for breast cancer detection
title_short Dynamic model scaling based on segmented tumor size for breast cancer detection
title_sort Dynamic model scaling based on segmented tumor size for breast cancer detection
topic Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Histopathology image
Breast cancer image segmentation and classification
Model scaling
Conditional diffusion probabilistic model