Logo image
Back
Integrating AI for Human-Centric Breast Cancer Diagnostics: A Multi-Scale and Multi-View Swin Transformer Framework
Conference proceeding   Open access

Integrating AI for Human-Centric Breast Cancer Diagnostics: A Multi-Scale and Multi-View Swin Transformer Framework

Farnoush Bayatmakou, Reza Taleei, Milad Amir Toutounchian and Arash Mohammadi
2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS), pp 87-92
26 May 2025
DOI: https://doi.org/10.1109/ICHMS65439.2025.11154329
url
https://arxiv.org/abs/2503.13309View
Preprint (Author's original) Open arXiv.org - Non-exclusive license to distribute

Abstract

Accuracy Annotations Artificial intelligence Feature extraction Mammography Multi-view Mammograms Robustness Synthetic data Transformer Transformers Breast Cancer Tumors
Despite advancements in Computer-Aided Diagnosis (CAD) systems, breast cancer remains one of the leading causes of cancer-related deaths among women worldwide. Recent Artificial Intelligence (AI) breakthroughs have shown significant promise in developing advanced Deep Learning (DL) architectures for breast cancer diagnosis through mammography. In this context, the paper focuses on integrating AI within a Human-Centric workflow to enhance breast cancer diagnostics. Key challenges are, however, largely overlooked, such as reliance on detailed tumor annotations and susceptibility to missing views, particularly during test time. To address these issues, we propose a hybrid, multi-scale and multi-view Swin Transformer-based framework (MSMV-Swin) that enhances diagnostic robustness and accuracy. The proposed MSMV-Swin framework is designed to be a decision-support tool, helping radiologists analyze multi-view mammograms more effectively. More specifically, the MSMV-Swin framework leverages the Segment Anything Model (SAM) to isolate the breast lobe, reducing background noise and enabling comprehensive feature extraction. The multi-scale nature of the proposed MSMV-Swin framework accounts for tumor-specific regions and the spatial characteristics of tissues surrounding the tumor, capturing both localized and contextual information. Integrating contextual and localized data ensures that MSMV-Swin's outputs align with how radiologists interpret mammograms, fostering better human-AI interaction and trust. A hybrid fusion structure is then designed to provide robustness against missing views, a common occurrence in clinical practice when only a single mammogram view is available. Experimental evaluations on single-view and dual-view mammography based on CBIS-DDSM dataset demonstrate the superior performance of MSMV-Swin, highlighting its potential for improving breast cancer diagnosis in diverse clinical settings.

Metrics

7 Record Views

Related content

Has preprint

Details

Logo image