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

2025-03-17

AI Summary

Current computer-aided diagnosis (CAD) systems for breast cancer suffer from three key limitations: reliance on labor-intensive, pixel-level tumor annotations; sensitivity to missing mammographic views; and misalignment with radiologists’ clinical workflow. To address these, we propose MSMV-Swin—a clinically oriented, multi-scale, multi-view Swin Transformer framework. It uniquely integrates SAM-guided coarse breast region segmentation, hierarchical multi-scale feature modeling, and a robust missing-view fusion mechanism, enabling flexible single- or dual-view inference while substantially reducing dependence on fine-grained annotations. The architecture explicitly emulates radiologists’ diagnostic reasoning, enhancing human-AI collaboration and clinical robustness. Evaluated on public benchmarks, MSMV-Swin achieves 98.2% accuracy and maintains 96.5% AUC under single-view input—outperforming state-of-the-art CAD methods. Preliminary clinical validation has been successfully conducted at a tertiary hospital.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Despite advancements in Computer-Aided Diagnosis (CAD) systems, breast cancer remains one of the leading causes of cancer-related deaths among women worldwide. Recent breakthroughs in Artificial Intelligence (AI) have shown significant promise in development of advanced Deep Learning (DL) architectures for breast cancer diagnosis through mammography. In this context, the paper focuses on the integration of 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 work as 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 as well as the spatial characteristics of tissues surrounding the tumor, capturing both localized and contextual information. The integration of contextual and localized data ensures that MSMV-Swin's outputs align with the way radiologists interpret mammograms, fostering better human-AI interaction and trust. A hybrid fusion structure is then designed to ensure robustness against missing views, a common occurrence in clinical practice when only a single mammogram view is available.

Problem

• Enhance breast cancer diagnostics using AI in human-centric workflows.
• Address challenges like reliance on tumor annotations and missing views.
• Propose a multi-scale, multi-view Swin Transformer framework for robust diagnosis.

Innovation

• Multi-scale Swin Transformer for diagnostics
• Segment Anything Model reduces background noise
• Hybrid fusion handles missing mammogram views