Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making
This study aims to improve breast cancer (BC) diagnosis through a novel multi-resolution Vision Transformer (ViT)-based framework with ensemble decision-making, addressing limitations in traditional single-magnification models. The proposed framework uses multiscale feature extraction at three magni...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11005972/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255700807122944 |
|---|---|
| author | Margo Sabry Hossam Magdy Balaha Khadiga M. Ali Tayseer Hassan A. Soliman Dibson Gondim Mohammed Ghazal Norah Saleh Alghamdi Ayman El-Baz |
| author_facet | Margo Sabry Hossam Magdy Balaha Khadiga M. Ali Tayseer Hassan A. Soliman Dibson Gondim Mohammed Ghazal Norah Saleh Alghamdi Ayman El-Baz |
| author_sort | Margo Sabry |
| collection | DOAJ |
| description | This study aims to improve breast cancer (BC) diagnosis through a novel multi-resolution Vision Transformer (ViT)-based framework with ensemble decision-making, addressing limitations in traditional single-magnification models. The proposed framework uses multiscale feature extraction at three magnification levels (L0, L1, L2 or 16x, 4x, 2x) to capture both fine-grained and high-level tumor features. A stacking ensemble method combines predictions from ViT models trained at these levels, improving classification robustness. Postprocessing techniques, including region-growing and fast-marching level set algorithms, refine whole-slide image (WSI) prediction and postprocessing quality. Performance was evaluated via metrics such as precision, recall, the F1 score, accuracy, and specificity across 50 trials with perturbed conditions. The framework achieved a top accuracy of 97.08%, with precision and recall above 94%. The suggested stack configuration outperformed individual models and other stacking configurations, demonstrating balanced performance with minimal variability. Statistical analysis highlighted the reliability and consistency of the framework under perturbed conditions. The multi-resolution ViT-based framework significantly improves BC classification by integrating multiscale analysis and ensemble decision-making. Its high accuracy and robustness make it a valuable tool for reducing interobserver variability in digital pathology workflows. |
| format | Article |
| id | doaj-art-7ce672b616174160bb2fb3e61c2c8347 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7ce672b616174160bb2fb3e61c2c83472025-08-20T01:56:48ZengIEEEIEEE Access2169-35362025-01-0113897048972210.1109/ACCESS.2025.357084011005972Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-MakingMargo Sabry0https://orcid.org/0009-0002-4770-960XHossam Magdy Balaha1https://orcid.org/0000-0002-0686-4411Khadiga M. Ali2https://orcid.org/0000-0001-7556-7173Tayseer Hassan A. Soliman3Dibson Gondim4https://orcid.org/0000-0003-0604-8403Mohammed Ghazal5https://orcid.org/0000-0002-9045-6698Norah Saleh Alghamdi6https://orcid.org/0000-0001-6421-6001Ayman El-Baz7https://orcid.org/0000-0001-7264-1323Information Systems Department, Assiut University, Asyut, EgyptBioengineering Department, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAPathology Department, Faculty of Medicine, Mansoura University, Mansoura, EgyptInformation Systems Department, Assiut University, Asyut, EgyptDepartment of Pathology, Laboratory Medicine, University of Louisville, Louisville, KY, USAElectrical, Computer, and Biomedical Engineering Department, Abu Dhabi University, Abu Dhabi, United Arab EmiratesDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi ArabiaBioengineering Department, J. B. Speed School of Engineering, University of Louisville, Louisville, KY, USAThis study aims to improve breast cancer (BC) diagnosis through a novel multi-resolution Vision Transformer (ViT)-based framework with ensemble decision-making, addressing limitations in traditional single-magnification models. The proposed framework uses multiscale feature extraction at three magnification levels (L0, L1, L2 or 16x, 4x, 2x) to capture both fine-grained and high-level tumor features. A stacking ensemble method combines predictions from ViT models trained at these levels, improving classification robustness. Postprocessing techniques, including region-growing and fast-marching level set algorithms, refine whole-slide image (WSI) prediction and postprocessing quality. Performance was evaluated via metrics such as precision, recall, the F1 score, accuracy, and specificity across 50 trials with perturbed conditions. The framework achieved a top accuracy of 97.08%, with precision and recall above 94%. The suggested stack configuration outperformed individual models and other stacking configurations, demonstrating balanced performance with minimal variability. Statistical analysis highlighted the reliability and consistency of the framework under perturbed conditions. The multi-resolution ViT-based framework significantly improves BC classification by integrating multiscale analysis and ensemble decision-making. Its high accuracy and robustness make it a valuable tool for reducing interobserver variability in digital pathology workflows.https://ieeexplore.ieee.org/document/11005972/Breast cancer (BC)computer-aided diagnosis (CAD)fast-marching level sethistopathologyVision Transformer (ViT)whole slide images (WSI) |
| spellingShingle | Margo Sabry Hossam Magdy Balaha Khadiga M. Ali Tayseer Hassan A. Soliman Dibson Gondim Mohammed Ghazal Norah Saleh Alghamdi Ayman El-Baz Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making IEEE Access Breast cancer (BC) computer-aided diagnosis (CAD) fast-marching level set histopathology Vision Transformer (ViT) whole slide images (WSI) |
| title | Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making |
| title_full | Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making |
| title_fullStr | Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making |
| title_full_unstemmed | Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making |
| title_short | Enhancing Breast Cancer Diagnosis With Multi-Resolution Vision Transformers and Robust Decision-Making |
| title_sort | enhancing breast cancer diagnosis with multi resolution vision transformers and robust decision making |
| topic | Breast cancer (BC) computer-aided diagnosis (CAD) fast-marching level set histopathology Vision Transformer (ViT) whole slide images (WSI) |
| url | https://ieeexplore.ieee.org/document/11005972/ |
| work_keys_str_mv | AT margosabry enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT hossammagdybalaha enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT khadigamali enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT tayseerhassanasoliman enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT dibsongondim enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT mohammedghazal enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT norahsalehalghamdi enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking AT aymanelbaz enhancingbreastcancerdiagnosiswithmultiresolutionvisiontransformersandrobustdecisionmaking |