Uncertainty-based quality assurance of carotid artery wall segmentation in black-blood MRI
This incremental work addresses the need for reliable quality assurance in applying deep learning models to large-scale medical imaging datasets, specifically for carotid artery segmentation.
The study tackled the problem of automatic quality assurance for carotid artery wall segmentation in black-blood MRI by investigating whether model uncertainty can serve as a proxy for error detection, finding that uncertainty metrics did not degrade segmentation quality and could detect low-quality segmentations at the participant level.
The application of deep learning models to large-scale data sets requires means for automatic quality assurance. We have previously developed a fully automatic algorithm for carotid artery wall segmentation in black-blood MRI that we aim to apply to large-scale data sets. This method identifies nested artery walls in 3D patches centered on the carotid artery. In this study, we investigate to what extent the uncertainty in the model predictions for the contour location can serve as a surrogate for error detection and, consequently, automatic quality assurance. We express the quality of automatic segmentations using the Dice similarity coefficient. The uncertainty in the model's prediction is estimated using either Monte Carlo dropout or test-time data augmentation. We found that (1) including uncertainty measurements did not degrade the quality of the segmentations, (2) uncertainty metrics provide a good proxy of the quality of our contours if the center found during the first step is enclosed in the lumen of the carotid artery and (3) they could be used to detect low-quality segmentations at the participant level. This automatic quality assurance tool might enable the application of our model in large-scale data sets.