MLV$^2$-Net: Rater-Based Majority-Label Voting for Consistent Meningeal Lymphatic Vessel Segmentation
This work addresses the difficulty of consistent MLV segmentation for medical imaging researchers, though it is incremental as it builds on the existing nnU-Net model.
The paper tackled the problem of segmenting meningeal lymphatic vessels (MLVs) in MRI, which is challenging due to high inter-rater variability in annotations, by proposing a rater-aware training scheme and ensembling strategies for nnU-Net, resulting in a Dice similarity coefficient of 0.806 and matching human inter-rater reliability.
Meningeal lymphatic vessels (MLVs) are responsible for the drainage of waste products from the human brain. An impairment in their functionality has been associated with aging as well as brain disorders like multiple sclerosis and Alzheimer's disease. However, MLVs have only recently been described for the first time in magnetic resonance imaging (MRI), and their ramified structure renders manual segmentation particularly difficult. Further, as there is no consistent notion of their appearance, human-annotated MLV structures contain a high inter-rater variability that most automatic segmentation methods cannot take into account. In this work, we propose a new rater-aware training scheme for the popular nnU-Net model, and we explore rater-based ensembling strategies for accurate and consistent segmentation of MLVs. This enables us to boost nnU-Net's performance while obtaining explicit predictions in different annotation styles and a rater-based uncertainty estimation. Our final model, MLV$^2$-Net, achieves a Dice similarity coefficient of 0.806 with respect to the human reference standard. The model further matches the human inter-rater reliability and replicates age-related associations with MLV volume.