medXGAN: Visual Explanations for Medical Classifiers Through a Generative Latent Space

Amil Dravid, Florian Schiffers, Boqing Gong, Aggelos K. Katsaggelos; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2936-2945

Abstract


Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization through latent interpolation. Furthermore, we optimize the latent space such that interpolation explains how the features contribute to the classifier's output. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability. Additionally, a combination of the medXGAN with Integrated Gradients can yield explanations more robust to noise. The project page with code is available at: https://avdravid.github.io/medXGAN page/.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Dravid_2022_CVPR, author = {Dravid, Amil and Schiffers, Florian and Gong, Boqing and Katsaggelos, Aggelos K.}, title = {medXGAN: Visual Explanations for Medical Classifiers Through a Generative Latent Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {2936-2945} }