Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

Jungo, Alain; Balsiger, Fabian; Reyes, Mauricio (2020). Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation. Frontiers in neuroscience, 14(282), p. 282. Frontiers Research Foundation 10.3389/fnins.2020.00282

[img]
Preview
Text
fnins-14-00282.pdf - Published Version
Available under License Creative Commons: Attribution (CC-BY).

Download (1MB) | Preview
[img]
Preview
Text
Data_Sheet_1_Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation.pdf - Supplemental Material
Available under License Creative Commons: Attribution (CC-BY).

Download (5MB) | Preview

Automatic segmentation of brain tumors has the potential to enable volumetric measures and high-throughput analysis in the clinical setting. Reaching this potential seems almost achieved, considering the steady increase in segmentation accuracy. However, despite segmentation accuracy, the current methods still do not meet the robustness levels required for patient-centered clinical use. In this regard, uncertainty estimates are a promising direction to improve the robustness of automated segmentation systems. Different uncertainty estimation methods have been proposed, but little is known about their usefulness and limitations for brain tumor segmentation. In this study, we present an analysis of the most commonly used uncertainty estimation methods in regards to benefits and challenges for brain tumor segmentation. We evaluated their quality in terms of calibration, segmentation error localization, and segmentation failure detection. Our results show that the uncertainty methods are typically well-calibrated when evaluated at the dataset level. Evaluated at the subject level, we found notable miscalibrations and limited segmentation error localization (e.g., for correcting segmentations), which hinder the direct use of the voxel-wise uncertainties. Nevertheless, voxel-wise uncertainty showed value to detect failed segmentations when uncertainty estimates are aggregated at the subject level. Therefore, we suggest a careful usage of voxel-wise uncertainty measures and highlight the importance of developing solutions that address the subject-level requirements on calibration and segmentation error localization.

Item Type:

Journal Article (Original Article)

Division/Institute:

10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research
10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research > ARTORG Center - AI in Medical Imaging Laboratory

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Jungo, Alain; Balsiger, Fabian and Reyes, Mauricio

Subjects:

500 Science > 570 Life sciences; biology
600 Technology > 610 Medicine & health

ISSN:

1662-4548

Publisher:

Frontiers Research Foundation

Language:

English

Submitter:

Alain Jungo

Date Deposited:

20 Nov 2020 17:26

Last Modified:

13 Mar 2021 12:21

Publisher DOI:

10.3389/fnins.2020.00282

PubMed ID:

32322186

BORIS DOI:

10.7892/boris.147562

URI:

https://boris.unibe.ch/id/eprint/147562

Actions (login required)

Edit item Edit item
Provide Feedback