Novel structural-scale uncertainty measures and error retention curves: application to multiple sclerosis
This work addresses clinically relevant segmentation and detection errors for multiple sclerosis patients, but it is incremental as it builds on existing uncertainty estimation methods.
The paper tackled uncertainty estimation for white matter lesion segmentation in MRI by proposing new lesion-scale uncertainty measures and extending an error retention curves framework, demonstrating that the proposed measure achieved the best performance on a multi-center testing set of 58 patients.
This paper focuses on the uncertainty estimation for white matter lesions (WML) segmentation in magnetic resonance imaging (MRI). On one side, voxel-scale segmentation errors cause the erroneous delineation of the lesions; on the other side, lesion-scale detection errors lead to wrong lesion counts. Both of these factors are clinically relevant for the assessment of multiple sclerosis patients. This work aims to compare the ability of different voxel- and lesion-scale uncertainty measures to capture errors related to segmentation and lesion detection, respectively. Our main contributions are (i) proposing new measures of lesion-scale uncertainty that do not utilise voxel-scale uncertainties; (ii) extending an error retention curves analysis framework for evaluation of lesion-scale uncertainty measures. Our results obtained on the multi-center testing set of 58 patients demonstrate that the proposed lesion-scale measure achieves the best performance among the analysed measures. All code implementations are provided at https://github.com/NataliiaMolch/MS_WML_uncs