Projects

Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection.

Moving beyond hyperintensity thresholding. This work analyzes the challenges and outlines opportunities for advancing the field of unsupervised anomaly detection.

Novel deformable auto-encoders for unsupervised outlier detection.

Implicit disentanglement of shape and appearance with federated learning for unsupervised brain pathology segmentation.