MLV$^2$-Net: Rater-Based Majority-Label Voting for Consistent Meningeal Lymphatic Vessel Segmentation

TL;DR

This paper introduces MLV$^2$-Net, a rater-aware ensemble model that improves the segmentation of meningeal lymphatic vessels in MRI, achieving high accuracy and replicating human inter-rater reliability.

Contribution

It proposes a novel rater-based training and ensembling approach for consistent MLV segmentation, addressing inter-rater variability and annotation style differences.

Findings

Achieves a Dice score of 0.806 on MLV segmentation

Matches human inter-rater reliability in predictions

Replicates age-related MLV volume associations

Abstract

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.