发表机构
Indiana University School of Medicine; Indiana University Melvin and Bren Simon Comprehensive Cancer Center; University of Warwick; Emory University; Radboud University Medical Center; Singapore General Hospital（印第安纳大学医学院; 印第安纳大学梅尔文与布伦·西蒙综合癌症中心; 华威大学; 埃默里大学; 拉德堡德大学医学中心; 新加坡中央医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述针对计算病理学（CompPath）中可解释人工智能（XAI）文献碎片化问题，建立病理学中心词汇、分类及任务驱动框架，明确XAI与临床部署的差距并提出推进建议。
AI 中文摘要
计算病理学（CompPath）正通过利用人工智能（AI）算法从千兆像素的全切片图像中支持诊断、预后和治疗预测，从而改变医学领域。临床应用正在推进，但受到高风险临床环境中对安全性、问责制和监管监督的担忧的限制。可解释人工智能（XAI）系统有望建立信任并实现验证，但由于术语不一致、方法家族重叠、临时验证以及现有综述的问题，相关文献仍处于碎片化状态。本综述旨在通过以下工作将CompPath中的XAI方法形式化：i）引入包含七个核心术语的以病理学为中心的词汇；ii）开发跨方法家族和三个正交轴（阶段、类型、范围）的分类；iii）建立将五个临床问题映射到推荐方法、方法评估和部署环境的任务驱动框架。研究还确定了当前XAI能力与临床部署之间的五个关键差距，并提出了可操作的步骤以推进CompPath的XAI发展。
英文摘要
Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and treatment prediction from gigapixel whole-slide images. Clinical adoption is progressing, but is constrained by concerns about safety, accountability, and regulatory oversight in high-stakes clinical environments. Explainable AI (XAI) systems hold promise for building trust and enabling verification, yet the literature remains fragmented due to inconsistent terminology, overlapping methodological families, ad hoc validation, and current reviews. This review aims to formalize XAI methods in CompPath through the: i) introduction of a pathology-centric vocabulary comprising seven core terms; ii) development of a taxonomy across methodological families and three orthogonal axes (stage, type, scope); and iii) establishment of a task-driven framework that maps five clinical questions to recommended methods, method evaluation, and deployment context. Five key gaps between current XAI capabilities and clinical deployment are identified, and actionable steps are proposed to advance XAI for CompPath.
CommentsOn behalf of MICCAI SIG-CompPath. More information: https://miccai.org/index.php/special-interest-groups/sig-comppath/
