Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods
This work addresses the challenge of interpreting generative models in medical image analysis, enabling unsupervised exploration without labeled data, which is incremental as it extends existing techniques from natural to medical images.
The paper tackled the problem of interpreting latent spaces of generative models for medical images by applying unsupervised methods to discover interpretable directions in GANs and VAEs trained on thoracic CT scans, finding directions corresponding to non-trivial transformations like rotation and breast size, and showing that these methods generalize across models and capture 3D structure from 2D data.
Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful directions corresponding to human-interpretable image transformations. However, until now, their exploration for medical images has been limited due to the requirement of supervised data. Several methods for unsupervised discovery of interpretable directions in GAN latent spaces have shown interesting results on natural images. This work explores the potential of applying these techniques on medical images by training a GAN and a VAE on thoracic CT scans and using an unsupervised method to discover interpretable directions in the resulting latent space. We find several directions corresponding to non-trivial image transformations, such as rotation or breast size. Furthermore, the directions show that the generative models capture 3D structure despite being presented only with 2D data. The results show that unsupervised methods to discover interpretable directions in GANs generalize to VAEs and can be applied to medical images. This opens a wide array of future work using these methods in medical image analysis.