Comparative evaluation of uncertainty estimation and decomposition methods on liver segmentation

ConclusionsMutual information decomposition is simple to implement, has mathematically pleasing properties, and yields meaningful uncertainty estimates that behave as expected under controlled changes to our data set. The additional extension of BNNs with loss-attenuating neurons provides no improvement in terms of segmentation performance or calibration in our setting, but marginal benefits regarding the quality of decomposed uncertainties.
Source: International Journal of Computer Assisted Radiology and Surgery - Category: Intensive Care Source Type: research