用视觉变压器精准识别紫外荧光乳腺癌图像，准确率达98.33%
Breast Cancer Classification in Deep Ultraviolet Fluorescence Images Using a Patch-Level Vision Transformer Framework
- 分块处理高分辨率图像，结合局部与全局特征
- 准确率98.33%，显著优于传统深度学习方法
- 可视化热力图提升医生对诊断结果的理解
保乳手术（BCS）旨在彻底切除恶性病灶的同时最大限度保留健康组织。术中切缘评估对于平衡癌症清除与组织保存至关重要。深紫外荧光扫描显微镜（DUV-FSM）可快速获取切除组织的全表面图像（WSIs），实现良恶性组织间的对比。然而，高分辨率和复杂的组织病理学特征给基于DUV-WSI的乳腺癌分类带来挑战。本研究提出一种基于分块视觉变压器（ViT）的DUV-WSI分类框架，有效捕捉局部与全局特征。Grad-CAM++显著性加权突出相关空间区域，增强结果可解释性，并提升良恶性组织分类的诊断准确性。五折交叉验证表明，该方法显著优于传统深度学习模型，分类准确率达到98.33%。
原文摘要 · Abstract (English)
Breast-conserving surgery (BCS) aims to completely remove malignant lesions while maximizing healthy tissue preservation. Intraoperative margin assessment is essential to achieve a balance between thorough cancer resection and tissue conservation. A deep ultraviolet fluorescence scanning microscope (DUV-FSM) enables rapid acquisition of whole surface images (WSIs) for excised tissue, providing contrast between malignant and normal tissues. However, breast cancer classification with DUV WSIs is challenged by high resolutions and complex histopathological features. This study introduces a DUV WSI classification framework using a patch-level vision transformer (ViT) model, capturing local and global features. Grad-CAM++ saliency weighting highlights relevant spatial regions, enhances result interpretability, and improves diagnostic accuracy for benign and malignant tissue classification. A comprehensive 5-fold cross-validation demonstrates the proposed approach significantly outperforms conventional deep learning methods, achieving a classification accuracy of 98.33%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。