Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation

Jungo, Alain; Reyes, Mauricio (2019). Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation. Lecture notes in computer science, 11765, pp. 48-56. Springer 10.1007/978-3-030-32245-8_6

Text 978-3-030-32245-8_6.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (324kB)

Despite the recent improvements in overall accuracy, deep learning systems still exhibit low levels of robustness. Detecting possible failures is critical for a successful clinical integration of these systems, where each data point corresponds to an individual patient. Uncertainty measures are a promising direction to improve failure detection since they provide a measure of a system’s confidence. Although many uncertainty estimation methods have been proposed for deep learning, little is known on their benefits and current challenges for medical image segmentation. Therefore, we report results of evaluating common voxel-wise uncertainty measures with respect to their reliability, and limitations on two medical image segmentation datasets. Results show that current uncertainty methods perform similarly and although they are well-calibrated at the dataset level, they tend to be miscalibrated at subject-level. Therefore, the reliability of uncertainty estimates is compromised, highlighting the importance of developing subject-wise uncertainty estimations. Additionally, among the benchmarked methods, we found auxiliary networks to be a valid alternative to common uncertainty methods since they can be applied to any previously trained segmentation model.

Interest & Impact

Downloads

1 since deposited on 28 Jan 2020
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item