Transformer-Based Explainable Deep Learning for Breast Cancer Detection in Mammography: The MammoFormer Framework

TL;DR

This paper introduces MammoFormer, a transformer-based framework for breast cancer detection in mammography that improves accuracy, provides explainability, and addresses clinical adoption barriers by combining multiple architectures and enhancement techniques.

Contribution

The MammoFormer framework uniquely integrates transformer architectures with feature enhancements and explainability for improved mammography analysis.

Findings

MammoFormer achieves up to 98.3% accuracy.

Transformer models with enhancements outperform CNNs.

Explainability features enhance clinical interpretability.

Abstract

Breast cancer detection through mammography interpretation remains difficult because of the minimal nature of abnormalities that experts need to identify alongside the variable interpretations between readers. The potential of CNNs for medical image analysis faces two limitations: they fail to process both local information and wide contextual data adequately, and do not provide explainable AI (XAI) operations that doctors need to accept them in clinics. The researcher developed the MammoFormer framework, which unites transformer-based architecture with multi-feature enhancement components and XAI functionalities within one framework. Seven different architectures consisting of CNNs, Vision Transformer, Swin Transformer, and ConvNext were tested alongside four enhancement techniques, including original images, negative transformation, adaptive histogram equalization, and histogram of oriented gradients. The MammoFormer framework addresses critical clinical adoption barriers of AI mammography systems through: (1) systematic optimization of transformer architectures via architecture-specific feature enhancement, achieving up to 13% performance improvement, (2) comprehensive explainable AI integration providing multi-perspective diagnostic interpretability, and (3) a clinically deployable ensemble system combining CNN reliability with transformer global context modeling. The combination of transformer models with suitable feature enhancements enables them to achieve equal or better results than CNN approaches. ViT achieves 98.3% accuracy alongside AHE while Swin Transformer gains a 13.0% advantage through HOG enhancements