Recent applications of deep convolutional neural networks in medical imaging raise concerns about their interpretability. While most explainable deep learning applications use post hoc methods (such as GradCAM) to generate feature attribution maps, there is a new type of case-based reasoning models, namely ProtoPNet and its variants, which identify prototypes during training and compare input image patches with those prototypes. We propose the first medical prototype network (MProtoNet) to extend ProtoPNet to brain tumor classification with 3D multi-parametric magnetic resonance imaging (mpMRI) data. To address different requirements between 2D natural images and 3D mpMRIs especially in terms of localizing attention regions, a new attention module with soft masking and online-CAM loss is introduced. Soft masking helps sharpen attention maps, while online-CAM loss directly utilizes image-level labels when training the attention module. MProtoNet achieves statistically significant improvements in interpretability metrics of both correctness and localization coherence (with a best activation precision of $0.713\pm0.058$) without human-annotated labels during training, when compared with GradCAM and several ProtoPNet variants. The source code is available at https://github.com/aywi/mprotonet.

翻译：近年来，深度卷积神经网络在医学影像中的应用引发了对其可解释性的担忧。尽管大多数可解释深度学习应用采用事后方法（如GradCAM）生成特征归因图，但新型基于案例推理的模型（即ProtoPNet及其变体）可在训练过程中识别原型，并将输入图像块与这些原型进行比对。我们首次提出医学原型网络（MProtoNet），将ProtoPNet扩展至基于3D多参数磁共振成像数据的脑肿瘤分类。为满足2D自然图像与3D多参数MRI在注意力区域定位方面的差异化需求，我们引入了包含软掩码和在线CAM损失的新注意力模块。软掩码能够锐化注意力图，而在线CAM损失在训练注意力模块时直接利用图像级标签。与GradCAM及多种ProtoPNet变体相比，MProtoNet在可解释性评估指标（正确性与定位连贯性）上均取得统计显著性提升（最佳激活精度达$0.713\pm0.058$），且训练中无需人工标注标签。源代码已发布于https://github.com/aywi/mprotonet。