Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. In this paper, we propose a novel interpretable approach that combines attribute regularization of the latent space within the framework of an adversarially trained variational autoencoder. Comparative experiments on a cardiac MRI dataset demonstrate the ability of the proposed method to address blurry reconstruction issues of variational autoencoder methods and improve latent space interpretability. Additionally, our analysis of a downstream task reveals that the classification of cardiac disease using the regularized latent space heavily relies on attribute regularized dimensions, demonstrating great interpretability by connecting the used attributes for prediction with clinical observations.

翻译：可解释性在医学影像中至关重要，以确保临床医生能够理解并信任人工智能模型。本文提出了一种新颖的可解释方法，该方法在对抗训练变分自编码器框架内结合了潜在空间的属性正则化。在心脏磁共振成像数据集上的对比实验表明，所提出的方法能够解决变分自编码器方法的模糊重建问题，并提升潜在空间的可解释性。此外，我们对下游任务的分析揭示，使用正则化潜在空间进行心脏病分类高度依赖于属性正则化维度，通过将用于预测的属性与临床观察相联系，展现了强大的可解释性。