AutoMIL：面向全切片图像分类的自动化多示例学习开源框架
AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification
AI 导读
研究者推出开源框架 AutoMIL，将自动机器学习方法应用于全切片病理图像分类，自动化预处理、训练与评估等关键流程。在默认设置的基准评测中，AutoMIL 在 UBC-OCEAN 上取得 ROC-AUC 0.94、PCam 上 0.99、TCGA-NSCLC 子集上 0.93-0.96，媲美专业化流程。集成主要在不平衡数据上提升性能，表明自动化流程需适配数据集特性。
正文 · 原文
Abstract:Developing multiple instance learning pipelines for the classification of whole-slide images involves many interdependent design decisions and expertise in both pathology and machine learning. We present AutoMIL, an open-source framework that applies principles from the field of automated machine learning to tackle this task by automating integral pipeline steps, such as preprocessing, training and evaluation. In a benchmark evaluation with default settings, AutoMIL reached ROC-AUC scores of 0.94 on UBC-OCEAN, 0.99 on PCam and 0.93-0.96 on a TCGA-NSCLC subset, comparable to specialised pipelines in related work. Ensembling mainly improved performance on imbalanced data, showing that an automated pipeline must adapt to dataset characteristics. AutoMIL thus provides an accessible baseline for whole-slide image classification without manual pipeline configuration.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32452 [cs.CV] |
| (or arXiv:2610.32452v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32452 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dominik Müller [view email]
[v1]
Fri, 23 Oct 2026 10:17:42 UTC (236 KB)
来源：arXiv cs.AI · arxiv.org