Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis

2026-06-02

AI Summary

This study addresses the challenge of time-consuming manual segmentation of the lateral ventricle choroid plexus (LVCP) in multiple sclerosis research, which hinders its clinical trial applicability. The authors propose an efficient automatic segmentation method based on SwinUNETR, employing a 32×32×32 voxel local patch sampling strategy to achieve precise segmentation on MPRAGE and/or FLAIR MRI sequences. By integrating a Transformer architecture with a localized region-focused mechanism, the approach maintains high accuracy while substantially reducing computational overhead. On an extended test set, the model achieves a mean Dice coefficient of 0.868, significantly outperforming 3D UXNET (p < 0.0001), with a 99% reduction in computational cost (91.8 vs. 22,080 GFLOPs) and improved Hausdorff distance at the 95th percentile (HD95).

Abstract

Background: The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physical disability and neuroinflammation. Yet, manual segmentation of the LVCP is highly tedious, restricting its use in broad clinical trials and longitudinal assessments. This research aims to develop a SwinUNETR-driven pipeline that leverages targeted intra- and peri-ventricular small patch sampling to automatically segment the LVCP in MS from both standalone and multi-modal MRI inputs. Methods: We retrospectively assessed 3T MRI scans across three sets of data stemming from two separate MS-dominant cohorts (Dataset 1: n=177; Dataset 2: n=177; expanded test set: n=388). Our method employed a SwinUNETR architecture trained on 32x32x32 voxel patches, benchmarking it against the 3D UXNET model. The primary metric for evaluation was the Dice Similarity Coefficient (DSC), supplemented by computational demand (GFLOPs) and the 95th percentile Hausdorff Distance (HD95). Results: On the extended test set, the SwinUNETR model secured a mean DSC of 0.868 (95% CI: 0.863-0.872) with MPRAGE and FLAIR combined, showing a statistically significant gain over UXNET (DSC: 0.858 [95% CI: 0.853-0.862], p<0.0001). When restricted to standalone FLAIR inputs, the transformer-based approach sustained a high DSC of 0.863, while the spatial localization of UXNET worsened considerably (HD95: 1.86 vs. 3.00 mm). Importantly, the proposed framework lowered computational load by 99% (91.8 vs. 22,080 GFLOPs). By integrating localized patch sampling with a SwinUNETR architecture, this methodology offers an accurate, robust, and statistically superior alternative to current leading models for LVCP segmentation. Its vast reduction in computational cost makes it ideal for widespread implementation in clinical and research environments.

Problem

• choroid plexus segmentation
• multiple sclerosis
• medical image analysis
• automated segmentation
• MRI

Innovation

• SwinUNETR
• localized patch sampling
• choroid plexus segmentation
• computational efficiency
• multi-modal MRI