Fig. 1: Proposed framework for uncertainty-aware GTVp segmentation of OPC patients. | Communications Medicine

Fig. 1: Proposed framework for uncertainty-aware GTVp segmentation of OPC patients.

From: Application of simultaneous uncertainty quantification and segmentation for oropharyngeal cancer use-case with Bayesian deep learning

Fig. 1

The probabilistic deep learning model (\(f(\,\cdot )\)) with stochastic parameters (\(\theta\)) distributed according to an approximate posterior distribution (\(p\)) segments the GTVp, outputs a voxel-level uncertainty map, and quantifies the patient-level uncertainty value (\(U\)). The patient-level uncertainty is then used to estimate the segmentation quality by checking whether the uncertainty is below or above the predetermined threshold (\(\tau\)). When the patient-level uncertainty exceeds the threshold, a medical expert will manually inspect and perform corrections to the deep learning segmentation, if necessary. The downstream utilization of the segmentation is then informed by the patient-wise and voxel-wise uncertainties, as well as the patient-wise performance estimate.

Back to article page