Finding novelty with uncertainty
This work addresses the problem of identifying pathology in medical images for healthcare applications, but it is incremental as it builds on existing uncertainty-based methods.
The paper tackles the challenge of unsupervised anomaly segmentation in medical images by proposing a Bayesian deep learning method that translates healthy CT images to MRI and computes voxel-wise uncertainty, achieving encouraging results with a novel scibilic uncertainty metric.
Medical images are often used to detect and characterize pathology and disease; however, automatically identifying and segmenting pathology in medical images is challenging because the appearance of pathology across diseases varies widely. To address this challenge, we propose a Bayesian deep learning method that learns to translate healthy computed tomography images to magnetic resonance images and simultaneously calculates voxel-wise uncertainty. Since high uncertainty occurs in pathological regions of the image, this uncertainty can be used for unsupervised anomaly segmentation. We show encouraging experimental results on an unsupervised anomaly segmentation task by combining two types of uncertainty into a novel quantity we call scibilic uncertainty.