让癌症病理切片自动发现关键形态特征，解释HPV预测结果
CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology
- 用注意力机制重构模型隐空间，无须标注即可发现形态概念
- 自动识别出角化、基底样等10个核心形态概念，精度与原模型相当
- 适合临床医生理解AI诊断依据，也适用于多种癌症病理分析
人乳头瘤病毒（HPV）状态是头颈部和宫颈癌预后及治疗反应的关键指标。尽管基于注意力的多实例学习（MIL）在全切片病理图像上实现了强滑块级预测，但其形态可解释性有限。为此，我们提出CLEAR-HPV框架，通过注意力加权重构MIL隐空间，实现无需概念标签的可解释概念发现。该框架在注意力加权隐空间中自动识别角化、基底样和间质等形态概念，生成空间概念图，并以仅10维的概念比例向量表示每张切片。该向量保留了原始MIL嵌入的预测能力，同时将高维特征空间（如1536维）压缩至可解释的低维表示。CLEAR-HPV在TCGA-HNSCC、TCGA-CESC和CPTAC-HNSCC数据集上均表现稳定，提供了一种通用、不依赖主干网络的注意力驱动MIL模型的可解释性解决方案。
原文摘要 · Abstract (English)
Human papillomavirus (HPV) status is a critical determinant of prognosis and treatment response in head and neck and cervical cancers. Although attention-based multiple instance learning (MIL) achieves strong slide-level prediction for HPV-related whole-slide histopathology, it provides limited morphologic interpretability. To address this limitation, we introduce Concept-Level Explainable Attention-guided Representation for HPV (CLEAR-HPV), a framework that restructures the MIL latent space using attention to enable concept discovery without requiring concept labels during training. Operating in an attention-weighted latent space, CLEAR-HPV automatically discovers keratinizing, basaloid, and stromal morphologic concepts, generates spatial concept maps, and represents each slide using a compact concept-fraction vector. CLEAR-HPV's concept-fraction vectors preserve the predictive information of the original MIL embeddings while reducing the high-dimensional feature space (e.g., 1536 dimensions) to only 10 interpretable concepts. CLEAR-HPV generalizes consistently across TCGA-HNSCC, TCGA-CESC, and CPTAC-HNSCC, providing compact, concept-level interpretability through a general, backbone-agnostic framework for attention-based MIL models of whole-slide histopathology.
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。