Deep learning and vision transformers-based framework for breast cancer and subtype identification

<p dir="ltr">Breast cancer, marked by uncontrolled cell growth in breast tissue, is the most common cancer among women and a second-leading cause of cancer-related deaths. Among its types, ductal and lobular carcinomas are the most prevalent, with invasive ductal carcinoma accounting...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ishrat Jahan (5782163) (author)
مؤلفون آخرون: Muhammad E. H. Chowdhury (14150526) (author), Semir Vranic (3353012) (author), Rafif Mahmood Al Saady (22330120) (author), Saidul Kabir (15302407) (author), Zahid Hasan Pranto (22330123) (author), Sabiha Jahan Mim (22330126) (author), Sadia Farhana Nobi (21512813) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513538468347904
author Ishrat Jahan (5782163)
author2 Muhammad E. H. Chowdhury (14150526)
Semir Vranic (3353012)
Rafif Mahmood Al Saady (22330120)
Saidul Kabir (15302407)
Zahid Hasan Pranto (22330123)
Sabiha Jahan Mim (22330126)
Sadia Farhana Nobi (21512813)
author2_role author
author
author
author
author
author
author
author_facet Ishrat Jahan (5782163)
Muhammad E. H. Chowdhury (14150526)
Semir Vranic (3353012)
Rafif Mahmood Al Saady (22330120)
Saidul Kabir (15302407)
Zahid Hasan Pranto (22330123)
Sabiha Jahan Mim (22330126)
Sadia Farhana Nobi (21512813)
author_role author
dc.creator.none.fl_str_mv Ishrat Jahan (5782163)
Muhammad E. H. Chowdhury (14150526)
Semir Vranic (3353012)
Rafif Mahmood Al Saady (22330120)
Saidul Kabir (15302407)
Zahid Hasan Pranto (22330123)
Sabiha Jahan Mim (22330126)
Sadia Farhana Nobi (21512813)
dc.date.none.fl_str_mv 2025-01-29T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s00521-025-10984-2
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Deep_learning_and_vision_transformers-based_framework_for_breast_cancer_and_subtype_identification/30233662
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
Breast cancer
Histopathology image
Hematoxylin–eosin (H&E)
Ductal carcinoma
Lobular carcinoma
Deep learning
Vision Transformer
dc.title.none.fl_str_mv Deep learning and vision transformers-based framework for breast cancer and subtype identification
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Breast cancer, marked by uncontrolled cell growth in breast tissue, is the most common cancer among women and a second-leading cause of cancer-related deaths. Among its types, ductal and lobular carcinomas are the most prevalent, with invasive ductal carcinoma accounting for about 70–80% of cases and invasive lobular carcinoma for about 10–15%. Accurate identification is crucial for effective treatment but can be time-consuming and prone to interobserver variability. AI can rapidly analyze pathological images, providing precise, cost-effective identification, thus reducing the pathologists’ workload. This study utilizes a deep learning framework for advanced, automatic breast cancer detection and subtype identification. The framework comprises three key components: detecting cancerous patches, identifying cancer subtypes (ductal and lobular carcinoma), and predicting patient-level outcomes from whole slide images (WSI). The validation process includes visualization using Score-CAM to highlight cancer-affected areas prominently. Datasets include 111 WSIs (85 malignant from the Warwick HER2 dataset and 26 benign from pathologists). For subtype detection, there are 57 ductal and 8 lobular carcinoma cases. A total of 28,428 annotated patches were reviewed by two expert pathologists. Four pre-trained models—DenseNet-201, MobileNetV2, an ensemble of these two, and a Vision Transformer-based model—were fine-tuned and tested on the patches. Patient-level results were predicted using a majority voting technique based on the percentage of each patch type in the WSI. The Vision Transformer-based model outperformed other models in patch classification, achieving an accuracy of 96.74% for cancerous patch detection and 89.78% for cancer subtype classification. For WSI-based cancer classification, the majority voting method attained an F1-score of 99.06 and 96.13% for WSI-based cancer subtype classification. The proposed deep learning-based framework for advanced breast cancer detection and subtype identification yielded promising results. This advanced framework shows great promise in medical practice, offering an economical, efficient solution for generating accurate, clinically relevant results and enhancing diagnostic accuracy in hospitals, research centers, and pathology laboratories. Nonetheless, further studies are needed to validate its effectiveness across various environments and larger datasets.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-025-10984-2" target="_blank">https://dx.doi.org/10.1007/s00521-025-10984-2</a></p>
eu_rights_str_mv openAccess
id Manara2_098d840e5a852013de600889819b561a
identifier_str_mv 10.1007/s00521-025-10984-2
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30233662
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Deep learning and vision transformers-based framework for breast cancer and subtype identificationIshrat Jahan (5782163)Muhammad E. H. Chowdhury (14150526)Semir Vranic (3353012)Rafif Mahmood Al Saady (22330120)Saidul Kabir (15302407)Zahid Hasan Pranto (22330123)Sabiha Jahan Mim (22330126)Sadia Farhana Nobi (21512813)Biomedical and clinical sciencesOncology and carcinogenesisHealth sciencesHealth services and systemsBreast cancerHistopathology imageHematoxylin–eosin (H&E)Ductal carcinomaLobular carcinomaDeep learningVision Transformer<p dir="ltr">Breast cancer, marked by uncontrolled cell growth in breast tissue, is the most common cancer among women and a second-leading cause of cancer-related deaths. Among its types, ductal and lobular carcinomas are the most prevalent, with invasive ductal carcinoma accounting for about 70–80% of cases and invasive lobular carcinoma for about 10–15%. Accurate identification is crucial for effective treatment but can be time-consuming and prone to interobserver variability. AI can rapidly analyze pathological images, providing precise, cost-effective identification, thus reducing the pathologists’ workload. This study utilizes a deep learning framework for advanced, automatic breast cancer detection and subtype identification. The framework comprises three key components: detecting cancerous patches, identifying cancer subtypes (ductal and lobular carcinoma), and predicting patient-level outcomes from whole slide images (WSI). The validation process includes visualization using Score-CAM to highlight cancer-affected areas prominently. Datasets include 111 WSIs (85 malignant from the Warwick HER2 dataset and 26 benign from pathologists). For subtype detection, there are 57 ductal and 8 lobular carcinoma cases. A total of 28,428 annotated patches were reviewed by two expert pathologists. Four pre-trained models—DenseNet-201, MobileNetV2, an ensemble of these two, and a Vision Transformer-based model—were fine-tuned and tested on the patches. Patient-level results were predicted using a majority voting technique based on the percentage of each patch type in the WSI. The Vision Transformer-based model outperformed other models in patch classification, achieving an accuracy of 96.74% for cancerous patch detection and 89.78% for cancer subtype classification. For WSI-based cancer classification, the majority voting method attained an F1-score of 99.06 and 96.13% for WSI-based cancer subtype classification. The proposed deep learning-based framework for advanced breast cancer detection and subtype identification yielded promising results. This advanced framework shows great promise in medical practice, offering an economical, efficient solution for generating accurate, clinically relevant results and enhancing diagnostic accuracy in hospitals, research centers, and pathology laboratories. Nonetheless, further studies are needed to validate its effectiveness across various environments and larger datasets.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00521-025-10984-2" target="_blank">https://dx.doi.org/10.1007/s00521-025-10984-2</a></p>2025-01-29T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00521-025-10984-2https://figshare.com/articles/journal_contribution/Deep_learning_and_vision_transformers-based_framework_for_breast_cancer_and_subtype_identification/30233662CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/302336622025-01-29T09:00:00Z
spellingShingle Deep learning and vision transformers-based framework for breast cancer and subtype identification
Ishrat Jahan (5782163)
Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Breast cancer
Histopathology image
Hematoxylin–eosin (H&E)
Ductal carcinoma
Lobular carcinoma
Deep learning
Vision Transformer
status_str publishedVersion
title Deep learning and vision transformers-based framework for breast cancer and subtype identification
title_full Deep learning and vision transformers-based framework for breast cancer and subtype identification
title_fullStr Deep learning and vision transformers-based framework for breast cancer and subtype identification
title_full_unstemmed Deep learning and vision transformers-based framework for breast cancer and subtype identification
title_short Deep learning and vision transformers-based framework for breast cancer and subtype identification
title_sort Deep learning and vision transformers-based framework for breast cancer and subtype identification
topic Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Breast cancer
Histopathology image
Hematoxylin–eosin (H&E)
Ductal carcinoma
Lobular carcinoma
Deep learning
Vision Transformer