提出可解释的病理图像分类模型，支持医生干预决策过程。
Prototype-Based Multiple Instance Learning for Gigapixel Whole Slide Image Classification
- 用稀疏自编码器提取可读性概念，构建线性组合决策机制。
- 在两个数据集上性能媲美顶尖MIL模型，且解释直观。
- 医生可修改输入概念，让模型因正确理由做出判断。
多实例学习（MIL）在组织病理学全切片图像（WSI）分析中表现优异，但多数模型仅提供基于注意力的解释，无法真实反映决策机制，也不支持人机交互。为此，本文提出ProtoMIL，一种内在可解释的WSI分析MIL模型，支持用户友好型解释并实现人工干预。该方法利用稀疏自编码器从图像特征空间中发现人类可理解的概念，并用于训练模型。预测结果以概念的线性组合形式表示，使决策过程透明。此外，用户可通过修改输入概念对模型进行干预。在两个常用病理数据集上的实验表明，ProtoMIL分类性能与当前最优MIL模型相当，同时提供直观可懂的解释。进一步证明，通过人工干预，可消除模型对诊断无关信息的依赖，引导其‘因正确理由’做出正确判断。代码将公开于https://github.com/ss-sun/ProtoMIL。
原文摘要 · Abstract (English)
Multiple Instance Learning (MIL) methods have succeeded remarkably in histopathology whole slide image (WSI) analysis. However, most MIL models only offer attention-based explanations that do not faithfully capture the model's decision mechanism and do not allow human-model interaction. To address these limitations, we introduce ProtoMIL, an inherently interpretable MIL model for WSI analysis that offers user-friendly explanations and supports human intervention. Our approach employs a sparse autoencoder to discover human-interpretable concepts from the image feature space, which are then used to train ProtoMIL. The model represents predictions as linear combinations of concepts, making the decision process transparent. Furthermore, ProtoMIL allows users to perform model interventions by altering the input concepts. Experiments on two widely used pathology datasets demonstrate that ProtoMIL achieves a classification performance comparable to state-of-the-art MIL models while offering intuitively understandable explanations. Moreover, we demonstrate that our method can eliminate reliance on diagnostically irrelevant information via human intervention, guiding the model toward being right for the right reason. Code will be publicly available at https://github.com/ss-sun/ProtoMIL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。