Bayesian Neural Networks for Uncertainty Estimation of Imaging Biomarkers
This work addresses the issue of unfaithful biomarker estimates in medical imaging for clinicians and researchers, though it is incremental as it builds on existing Bayesian neural network methods.
The paper tackled the problem of segmentation quality variation affecting imaging biomarker analysis by proposing to propagate segmentation uncertainty into statistical models, resulting in improved statistical inference for liver segmentation in diabetic patients.
Image segmentation enables to extract quantitative measures from scans that can serve as imaging biomarkers for diseases. However, segmentation quality can vary substantially across scans, and therefore yield unfaithful estimates in the follow-up statistical analysis of biomarkers. The core problem is that segmentation and biomarker analysis are performed independently. We propose to propagate segmentation uncertainty to the statistical analysis to account for variations in segmentation confidence. To this end, we evaluate four Bayesian neural networks to sample from the posterior distribution and estimate the uncertainty. We then assign confidence measures to the biomarker and propose statistical models for its integration in group analysis and disease classification. Our results for segmenting the liver in patients with diabetes mellitus clearly demonstrate the improvement of integrating biomarker uncertainty in the statistical inference.