Validating Uncertainty in Medical Image Translation
Authors:
- 1 April 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 95-98
Abstract
Medical images are increasingly used as input to deep neural networks to produce quantitative values that aid researchers and clinicians. However, standard deep neural networks do not provide a reliable measure of uncertainty in those quantitative values. Recent work has shown that using dropout during training and testing can provide estimates of uncertainty. In this work, we investigate using dropout to estimate epistemic and aleatoric uncertainty in a CT-to-MR image translation task. We show that both types of uncertainty are captured, as defined, providing confidence in the output uncertainty estimates.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Finding novelty with uncertainty2020
- Evaluating the impact of intensity normalization on MR image synthesis2019
- Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation2018
- Uncertainty in Multitask Learning: Joint Representations for Probabilistic MR-only Radiotherapy Planning2018
- Whole Brain Segmentation and Labeling from CT Using Synthetic MR Images2017
- Deconvolution and Checkerboard Artifacts2016
- Efficient object localization using Convolutional Networks2015
- Aleatory or epistemic? Does it matter?Structural Safety, 2009