发表机构
School of Electrical Engineering, Korea University（高丽大学电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出无需训练的即插即用测试时实例选择框架TTIS，融入多视图集成策略，可无缝集成到现有MIL模型，在多个WSI分析基准任务中性能优于或匹配基线模型。
AI 中文摘要
全切片图像（Whole Slide Image, WSI）分析已被广泛研究用于癌症诊断。传统方法中，千兆像素级的WSI被划分为小图块，再由多实例学习（Multiple Instance Learning, MIL）模型处理。然而，现有MIL模型通常会处理所有图块，其中许多包含冗余或无信息的组织模式。尽管近期研究聚焦于实例选择以识别有判别性的图块并减少冗余，但这些选择模块仍需要额外训练。本研究提出测试时实例选择（Test-Time Instance Selection, TTIS），这是一种无需训练、即插即用的框架，可在推理过程中选择紧凑且具代表性的图块。TTIS进一步融入多视图集成策略，整合组织形态的不同维度，提升鲁棒性。重要的是，TTIS可无缝集成到现有MIL模型中，无需重新训练或修改架构，支持灵活部署。在多个基准上的广泛评估表明，该方法在一系列分类和亚型任务中，性能优于或匹配基线MIL模型，其实现代码可在指定URL获取。
英文摘要
Whole Slide Image (WSI) analysis has been widely studied for cancer diagnosis. Conventionally, a gigapixel WSI is divided into small patches and processed by Multiple Instance Learning (MIL) models. However, existing MIL models typically process all patches, many of which contain redundant or non-informative tissue patterns. Although recent approaches have focused on instance selection to identify discriminative patches and reduce redundancy, these selection modules still require additional training. In this work, we propose Test-Time Instance Selection (TTIS), a training-free, plug-and-play framework that selects compact yet representative patches during inference. TTIS further incorporates a multi-view ensemble strategy to integrate distinct facets of tissue morphology, enhancing robustness. Importantly, TTIS can be seamlessly integrated into existing MIL models without retraining or architectural changes, enabling flexible deployment. Extensive evaluations across multiple benchmarks demonstrate that our approach improves or matches baseline MIL performance across a range of classification and subtyping tasks. Our implementation code is available at https://github.com/QuIIL/TTIS
CommentsAccepted at The 2nd MICCAI Workshop on Efficient Medical AI (EMA4MICCAI 2026)
