Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
The Journal of Machine Learning for Biomedical Imaging, vol. 2024, pp. 1048–1082
Abstract
Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the “utility” of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, c.f. head-and-neck CT and prostate MR scans. Uncertainty heatmaps (i.e. predictive entropy) are evaluated against voxel inaccuracies using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available at https://github.com/prerakmody/bayesuncertainty-error-correspondence
Authors 8
-
Prerak Mody Aachen Department of Radiology, Leiden University Medical Center Department of Radiation Oncology
Leiden University Medical Center · Erasmus MC · University Medical Center Utrecht · Holland Particle Therapy Center · Delft University of Technology
Affiliation as printed
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
HollandPTC consortium – Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft, Leiden
University Medical Center, Leiden and TU Delft, Delft, The Netherlands
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
Leiden University Medical Center, Leiden and TU Delft, Delft, The Netherlands
-
Delft University of Technology
Affiliation as printed
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
-
Chinmay Rao Aachen Department of Radiology, Leiden University Medical Center Department of Radiation Oncology
Leiden University Medical Center · Erasmus MC · University Medical Center Utrecht · Holland Particle Therapy Center · Delft University of Technology
Affiliation as printed
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
HollandPTC consortium -Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft,
Leiden University Medical Center, Leiden and TU Delft, Delft, The Netherlands
-
Leiden University Medical Center
Affiliation as printed
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
-
University Medical Center Utrecht
Affiliation as printed
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
-
Nienke Hoekstra Aachen Department of Radiation Oncology Department of Radiology, Leiden University Medical Center
Leiden University Medical Center · Erasmus MC · University Medical Center Utrecht · Holland Particle Therapy Center · Delft University of Technology
Affiliation as printed
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
HollandPTC consortium -Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft,
Leiden University Medical Center, Leiden and TU Delft, Delft, The Netherlands
-
Klaus Hildebrandt Aachen Department of Radiation Oncology Department of Radiology, Leiden University Medical Center
Leiden University Medical Center · Erasmus MC · University Medical Center Utrecht · Holland Particle Therapy Center · Delft University of Technology
Affiliation as printed
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
HollandPTC consortium -Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft,
Leiden University Medical Center, Leiden and TU Delft, Delft, The Netherlands
-
Marius Staring Aachen Department of Radiation Oncology Department of Radiology, Leiden University Medical Center
Leiden University Medical Center · Erasmus MC · University Medical Center Utrecht · Holland Particle Therapy Center · Delft University of Technology
Affiliation as printed
Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
Computer Graphics and Visualization Group , EEMCS, TU Delft, Delft, The Netherlands
Department of Radiation Oncology, University Medical Center, Utrecht, The Netherlands
HollandPTC consortium -Erasmus Medical Center, Rotterdam, Holland Proton Therapy Centre, Delft,
Leiden University Medical Center, Leiden and TU Delft, Delft, The Netherlands
Cited by 2 stored of 2
2 results
No patents citing this paper on Lens.org (checked 2026-10-11).