发表机构
Concordia University; McGill University; Mila – Quebec AI Institute（康考迪亚大学; 麦吉尔大学; Mila – 魁北克人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MFE-MIL，一种特征空间掩码框架，联合训练MLP适配器与掩码重建分支，抑制切片内差异，在多个病理数据集上提升分类与生存预测性能。
AI 中文摘要
计算病理学中的全切片图像（WSI）分析遵循多实例学习（MIL）流程，其中补丁嵌入被独立提取并聚合以进行切片级预测，但切片内因染色、扫描仪和局部纹理引起的差异可能淹没判别性信号。我们提出掩码特征编码多实例学习（MFE-MIL），一种特征空间掩码框架，它联合训练一个轻量级MLP适配器、一个基于窗口的掩码重建分支和一个MIL分类头。这两个目标是互补的。分类引导适配器抑制切片内补丁差异，而基于窗口的掩码重建为适配后的特征提供辅助正则化，无需使用补丁坐标、坐标图或分割预处理。光栅补丁提取顺序仅用作弱隐式先验。在推理时，解码器被移除，仅保留适配器和MIL头。在CAMELYON16/17、PANDA和TCGA-BRCA上使用四种不同的编码器，MFE-MIL在几乎所有测试的聚合器-编码器设置中提高了ACC/F1，在大多数设置中提高了AUC，优于基于坐标的空间方法（CAMIL），并在四个数据集中的三个（UNI）上实现了比2DMamba更高的AUC。在五个TCGA生存队列中，它提高了每个测试聚合器的平均一致性指数，这是其最一致的增益。代码可在该https URL获取。
英文摘要
Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are extracted independently and aggregated for slide-level prediction, but within-slide variance from staining, scanner, and local texture can overwhelm the discriminative signal. We propose Masked Feature Encoding for Multiple Instance Learning (MFE-MIL), a feature-space masking framework that trains a lightweight MLP adapter jointly with a window-based masked reconstruction branch and a MIL classification head. The two objectives are complementary. Classification guides the adapter to suppress within-slide patch variance, while window-based masked reconstruction provides an auxiliary regularizer for the adapted features without using patch coordinates, coordinate graphs, or segmentation preprocessing. The raster patch-extraction order is used only as a weak implicit prior. At inference, the decoder is removed, leaving only the adapter and MIL head. Across CAMELYON16/17, PANDA, and TCGA-BRCA with four diverse encoders, MFE-MIL improves ACC/F1 for nearly all tested aggregator-encoder settings and AUC in most, outperforms coordinate-based spatial methods (CAMIL), and achieves higher AUC than 2DMamba on three of four datasets (UNI). On five TCGA survival cohorts it improves the average concordance index for every aggregator tested, its most consistent gain. Code is available at https://github.com/AtlasAnalyticsLab/MFE-MIL.
CommentsAccepted at ACCV 2026
