Physical Sciences and Mathematics Commons^™

Trustworthy Medical Segmentation With Uncertainty Estimation, Giuseppina Carannante, Dimah Dera, Nidhal C. Bouaynaya, Rasool Ghulam, Hassan M. Fathallah-Shaykh

Computer Science Faculty Publications and Presentations

Deep Learning (DL) holds great promise in reshaping the healthcare systems given its precision, efficiency, and objectivity. However, the brittleness of DL models to noisy and out-of-distribution inputs is ailing their deployment in the clinic. Most systems produce point estimates without further information about model uncertainty or confidence. This paper introduces a new Bayesian deep learning framework for uncertainty quantification in segmentation neural networks, specifically encoder-decoder architectures. The proposed framework uses the first-order Taylor series approximation to propagate and learn the first two moments (mean and covariance) of the distribution of the model parameters given the training data by maximizing …