Pseudo-healthy synthesis with pathology disentanglement and adversarial learning
This work addresses the problem of anomaly detection and disease understanding in medical imaging for clinicians and researchers, though it appears incremental as it builds on existing disentanglement and adversarial learning methods.
The paper tackles pseudo-healthy synthesis by developing a model that disentangles pathology from healthy tissue to generate subject-specific healthy images from pathological ones, showing it outperforms baselines on datasets like ISLES, BraTS, and Cam-CAN with quantitative and human evaluations.
Pseudo-healthy synthesis is the task of creating a subject-specific `healthy' image from a pathological one. Such images can be helpful in tasks such as anomaly detection and understanding changes induced by pathology and disease. In this paper, we present a model that is encouraged to disentangle the information of pathology from what seems to be healthy. We disentangle what appears to be healthy and where disease is as a segmentation map, which are then recombined by a network to reconstruct the input disease image. We train our models adversarially using either paired or unpaired settings, where we pair disease images and maps when available. We quantitatively and subjectively, with a human study, evaluate the quality of pseudo-healthy images using several criteria. We show in a series of experiments, performed on ISLES, BraTS and Cam-CAN datasets, that our method is better than several baselines and methods from the literature. We also show that due to better training processes we could recover deformations, on surrounding tissue, caused by disease. Our implementation is publicly available at https://github.com/xiat0616/pseudo-healthy-synthesis. This paper has been accepted by Medical Image Analysis: https://doi.org/10.1016/j.media.2020.101719.