Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis

TL;DR

This paper introduces Axial-MLP, a novel neural network architecture for automatic segmentation of the choroid plexus in MRI scans, showing promising results compared to existing methods and highlighting its potential for large-scale MS studies.

Contribution

The paper proposes Axial-MLP, a new MLP-based model for CP segmentation, and systematically compares it with U-Net variants and FreeSurfer, demonstrating its viability as an alternative.

Findings

Deep learning methods outperform FreeSurfer in CP segmentation.

Axial-MLP achieves competitive accuracy with U-Nets.

Deep learning tools can facilitate large cohort studies in MS.

Abstract

Choroid plexuses (CP) are structures of the ventricles of the brain which produce most of the cerebrospinal fluid (CSF). Several postmortem and in vivo studies have pointed towards their role in the inflammatory process in multiple sclerosis (MS). Automatic segmentation of CP from MRI thus has high value for studying their characteristics in large cohorts of patients. To the best of our knowledge, the only freely available tool for CP segmentation is FreeSurfer but its accuracy for this specific structure is poor. In this paper, we propose to automatically segment CP from non-contrast enhanced T1-weighted MRI. To that end, we introduce a new model called "Axial-MLP" based on an assembly of Axial multi-layer perceptrons (MLPs). This is inspired by recent works which showed that the self-attention layers of Transformers can be replaced with MLPs. This approach is systematically compared with a standard 3D U-Net, nnU-Net, Freesurfer and FastSurfer. For our experiments, we make use of a dataset of 141 subjects (44 controls and 97 patients with MS). We show that all the tested deep learning (DL) methods outperform FreeSurfer (Dice around 0.7 for DL vs 0.33 for FreeSurfer). Axial-MLP is competitive with U-Nets even though it is slightly less accurate. The conclusions of our paper are two-fold: 1) the studied deep learning methods could be useful tools to study CP in large cohorts of MS patients; 2)~Axial-MLP is a potentially viable alternative to convolutional neural networks for such tasks, although it could benefit from further improvements.