Region-Affinity Attention for Whole-Slide Breast Cancer Classification in Deep Ultraviolet Imaging

TL;DR

This paper presents a novel Region-Affinity Attention mechanism for whole-slide breast cancer classification using Deep Ultraviolet imaging, improving spatial context modeling and diagnostic accuracy over existing methods.

Contribution

It introduces a slide-level attention mechanism that models regional relationships without patching, enhancing diagnostic specificity in DUV-WSI breast cancer classification.

Findings

Achieved 92.67% accuracy and 95.97% AUC on DUV-WSI dataset.

Outperformed existing attention mechanisms in classification performance.

Processed entire slides to preserve spatial integrity and improve diagnosis.

Abstract

Breast cancer diagnosis demands rapid and precise tools, yet traditional histopathological methods often fall short in intra-operative settings. Deep Ultraviolet (DUV) fluorescence imaging emerges as a transformative approach, offering high-contrast, label-free visualization of whole-slide images (WSIs) with unprecedented detail, surpassing conventional hematoxylin and eosin (H&E) staining in speed and resolution. However, existing deep learning methods for breast cancer classification, predominantly patch-based, fragment spatial context and incur significant preprocessing overhead, limiting their clinical utility. Moreover, standard attention mechanisms, such as Spatial, Squeeze-and-Excitation, Global Context and Guided Context Gating, fail to fully exploit the rich, multi-scale regional relationships inherent in DUV-WSI data, often prioritizing generic feature recalibration over diagnostic specificity. This study introduces a novel Region-Affinity Attention mechanism tailored for DUV-WSI breast cancer classification, processing entire slides without patching to preserve spatial integrity. By modeling local neighbor distances and constructing a full affinity matrix, our method dynamically highlights diagnostically relevant regions, augmented by a contrastive loss to enhance feature discriminability. Evaluated on a dataset of 136 DUV-WSI samples, our approach achieves an accuracy of 92.67 +/- 0.73% and an AUC of 95.97%, outperforming existing attention methods.