Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
Open Access
- 1 August 2024
- journal article
- Published by Machine Learning for Biomedical Imaging in Machine Learning for Biomedical Imaging
- Vol. 2 (August 202) , 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-correspondenceKeywords
All Related Versions
This publication has 17 references indexed in Scilit:
- ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentationPattern Recognition, 2022
- Barriers and facilitators to clinical implementation of radiotherapy treatment planning automation: A survey study of medical dosimetristsJournal of Applied Clinical Medical Physics, 2022
- Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationComputerized Medical Imaging and Graphics, 2022
- Deep Bayesian baseline for segmenting diabetic retinopathy lesions: Advances and challengesComputers in Biology and Medicine, 2021
- Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRIComputer Methods and Programs in Biomedicine, 2021
- Clinical Evaluation of Deep Learning and Atlas-Based Auto-Contouring of Bladder and Rectum for Prostate Radiation TherapyPractical Radiation Oncology, 2021
- Exploring uncertainty measures in deep networks for Multiple sclerosis lesion detection and segmentationMedical Image Analysis, 2020
- Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound imagesMedical Image Analysis, 2019
- Interobserver variability in delineation of target volumes in head and neck cancerRadiotherapy and Oncology, 2019
- Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networksNeurocomputing, 2019