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

2026-04-18

AI Summary

This study addresses the critical trade-off between speed and accuracy in intraoperative pathological diagnosis, where existing deep learning approaches relying on image patching disrupt whole-slide spatial context and struggle to model multiscale regional associations under deep ultraviolet (DUV) imaging. To overcome these limitations, this work proposes a region affinity attention mechanism that enables end-to-end processing of entire whole-slide images for the first time. By constructing a global affinity matrix based on local neighborhood distances, the model dynamically focuses on diagnostically relevant regions and incorporates contrastive loss to enhance feature discriminability. Evaluated on a dataset of 136 DUV-stained whole-slide breast cancer specimens, the proposed method achieves an accuracy of 92.67 ± 0.73% and an AUC of 95.97%, significantly outperforming current attention-based approaches and demonstrating improved clinical applicability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• whole-slide imaging
• breast cancer classification
• deep ultraviolet imaging
• spatial context
• attention mechanism

Innovation

• Region-Affinity Attention
• Deep Ultraviolet Imaging
• Whole-Slide Image Classification
• Contrastive Loss
• Spatial Context Preservation