The black-box nature of deep learning models has raised concerns about their interpretability for successful deployment in real-world clinical applications. To address the concerns, eXplainable Artificial Intelligence (XAI) aims to provide clear and understandable explanations of the decision-making process. In the medical domain, concepts such as attributes of lesions or abnormalities serve as key evidence for deriving diagnostic results. Existing concept-based models mainly depend on concepts that appear independently and require fine-grained concept annotations such as bounding boxes. However, a medical image usually contains multiple concepts, and the fine-grained concept annotations are difficult to acquire. In this paper, we aim to interpret representations in deep neural networks by aligning the axes of the latent space with known concepts of interest. We propose a novel Concept-Attention Whitening (CAW) framework for interpretable skin lesion diagnosis. CAW is comprised of a disease diagnosis branch and a concept alignment branch. In the former branch, we train a convolutional neural network (CNN) with an inserted CAW layer to perform skin lesion diagnosis. The CAW layer decorrelates features and aligns image features to conceptual meanings via an orthogonal matrix. In the latter branch, the orthogonal matrix is calculated under the guidance of the concept attention mask. We particularly introduce a weakly-supervised concept mask generator that only leverages coarse concept labels for filtering local regions that are relevant to certain concepts, improving the optimization of the orthogonal matrix. Extensive experiments on two public skin lesion diagnosis datasets demonstrated that CAW not only enhanced interpretability but also maintained a state-of-the-art diagnostic performance.

翻译：深度学习模型的黑箱特性引发了对其在真实世界临床应用中的可解释性的担忧。为解决这一问题，可解释人工智能旨在为决策过程提供清晰易懂的解释。在医学领域，病变属性或异常等概念是推导诊断结果的关键证据。现有的基于概念的模型主要依赖于独立出现的概念，并需要细粒度的概念标注（如边界框）。然而，医学图像通常包含多个概念，且细粒度的概念标注难以获取。本文旨在通过将潜在空间的坐标轴与已知关注概念对齐，来解释深度神经网络中的表示。我们提出了一种新颖的概念注意力白化框架，用于可解释的皮肤病变诊断。CAW由疾病诊断分支和概念对齐分支组成。在前一分支中，我们训练一个插入CAW层的卷积神经网络以执行皮肤病变诊断。CAW层通过正交矩阵对特征进行去相关，并将图像特征与概念含义对齐。在后一分支中，正交矩阵在概念注意力掩码的指导下计算。我们特别引入了一种弱监督概念掩码生成器，该生成器仅利用粗粒度概念标签来筛选与特定概念相关的局部区域，从而改进正交矩阵的优化。在两个公开皮肤病变诊断数据集上的大量实验表明，CAW不仅增强了可解释性，同时保持了最先进的诊断性能。