Automated Detection of Cortical Lesions in Multiple Sclerosis Patients with 7T MRI

TL;DR

This study presents a deep learning approach using a simplified 3D U-Net to detect cortical lesions in MS patients with 7T MRI, achieving promising detection rates and supporting expert manual segmentation.

Contribution

The paper introduces a novel deep learning method with data augmentation for automated cortical lesion detection in 7T MRI, improving upon baseline performance.

Findings

Achieved 67% lesion-wise detection rate

False positive rate of 42%, with many confirmed as true lesions

Enhanced detection performance by adding tissue segmentation and input channel dropout

Abstract

The automated detection of cortical lesions (CLs) in patients with multiple sclerosis (MS) is a challenging task that, despite its clinical relevance, has received very little attention. Accurate detection of the small and scarce lesions requires specialized sequences and high or ultra-high field MRI. For supervised training based on multimodal structural MRI at 7T, two experts generated ground truth segmentation masks of 60 patients with 2014 CLs. We implemented a simplified 3D U-Net with three resolution levels (3D U-Net-). By increasing the complexity of the task (adding brain tissue segmentation), while randomly dropping input channels during training, we improved the performance compared to the baseline. Considering a minimum lesion size of 0.75 {\mu}L, we achieved a lesion-wise cortical lesion detection rate of 67% and a false positive rate of 42%. However, 393 (24%) of the lesions reported as false positives were post-hoc confirmed as potential or definite lesions by an expert. This indicates the potential of the proposed method to support experts in the tedious process of CL manual segmentation.