发表机构
University of Geneva; University of Applied Sciences Western Switzerland (HES-SO Valais)（日内瓦大学; 瑞士西部应用科学大学（HES-SO Valais））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出弱监督BoVW流程，从ROI学习视觉词汇并生成LUAD空间模式图，在肿瘤/健康和组织学分级分类任务中表现优于或接近现有方法，可保留与分级相关的异质性。
AI 中文摘要
对肺腺癌（LUAD）在全切片图像（WSI）上的生长模式进行空间映射，需要在区域层面解析结构上下文，但现有方法仅在单个图块层面操作，生成的是通用形态学聚类而非临床定义的模式图。本文提出一种弱监督视觉词袋（BoVW）流程，该流程从少量标注感兴趣区域（ROI）中提取的冻结基础模型嵌入学习视觉词汇；模式原型被构造为相同标签ROI的平均BoVW直方图，用于在Jensen-Shannon散度下对滑动窗口区域进行近邻原型分类；将所得预测结果投影到WSI图块网格上，生成可解释的空间模式图。在87名CPTAC-LUAD患者上，采用3种基础模型编码器并针对2个临床任务、使用多种词汇规模对该方法进行评估：在肿瘤/健康分类任务中，采用H-Optimus-1的最佳配置达到0.974的平衡准确率，接近基于平均池化WSI嵌入训练的监督SVM所取得的0.987；在组织学分级二分类任务中，BoVW流程在所有编码器上均取得比监督基线更高的平衡准确率，表明ROI层面的模式分解保留了与分级相关的异质性，而全局平均池化会削弱这种异质性。
英文摘要
Spatial mapping of lung adenocarcinoma (LUAD) growth patterns across whole slide images (WSIs) requires resolving architectural context at the region level, yet existing methods operate at the individual tile level and produce generic morphological clusters rather than clinically defined pattern maps. We propose a weakly supervised Bag-of-Visual-Words (BoVW) pipeline that learns a visual vocabulary from frozen foundation model embeddings extracted from a small set of annotated regions of interest (ROIs). Pattern prototypes are constructed as mean BoVW histograms of same-label ROIs and used for nearest-prototype classification of sliding-window regions under Jensen--Shannon divergence. The resulting predictions are projected onto the WSI tile grid to produce interpretable spatial pattern maps. We evaluate the method on 87 CPTAC-LUAD patients using three foundation model encoders and multiple vocabulary sizes on two clinically motivated tasks. For tumour/healthy classification, the best configuration achieves a balanced accuracy of $0.974$ with H-Optimus-1, approaching the $0.987$ obtained by a supervised SVM trained on mean-pooled WSI embeddings. For binary histologic grade classification, the BoVW pipeline achieves higher balanced accuracy than the supervised baseline for all encoders, suggesting that ROI-level pattern decomposition preserves grade-relevant heterogeneity that is attenuated by global mean pooling.
Comments10 pages, 2 figures. Accepted at the 7th International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2026)
