Comparison of Automated White Matter Lesion Segmentation Approaches for Use in Large, Multi-Site Data Analyses in Parkinson's Disease

BackgroundParkinsons disease (PD) is the second most common neurodegenerative disorder. PD currently lacks effective disease-modifying treatments, likely due to its diverse clinical features and underlying neuropathology. The vascular role in PD is emerging, with vascular mechanisms increasingly implicated, yet the literature remains conflicted, motivating large-data analyses with greater statistical power. White matter lesions (WML) are an accepted imaging marker of small vessel disease. Accurate automated WML segmentation techniques are crucial for large-scale studies in PD due to the impracticality of manual segmentation for extensive datasets and to ensure consistency. Evaluation of the optimum approach in PD for large-scale analysis is lacking. This study aimed to evaluate various automated WML segmentation algorithms to determine the most accurate and reliable method, among those selected, for assessing WML for multi-site large data analysis in PD. MethodsWe assessed whole-brain volumetric T1-weighted and FLAIR images from 201 PD patients (mean age, 66.6 {+/-} 7.86 years) and 64 healthy controls (HC; mean age, 66.3 {+/-} 8.67) across three datasets: the Parkinsons Progression Markers Initiative (PPMI), the University of Pennsylvania (UPenn) and the Montreal Neurological Institute Biobank: Clinical Biological Imaging and Genetic Repository (C-BIG). The sample included different scanners, imaging parameters and lesion loads, as would be expected for multi-site data. WML were manually segmented to provide the gold standard, and four freely available automated algorithms were evaluated: FSLs BIANCA, FreeSurfer, SPMs LST-LPA and U-Net-pgs using the performance metrics: Dice score, Hausdorff distance, recall, precision, F1 score, log absolute volume difference (LOGAVD) and intraclass correlation coefficient (ICC). Subgroup analyses were performed based on lesion load and lobar regions. The associations of data from these automated approaches with age, and with Fazekas and Wahlund visual rating scales, were assessed through partial correlation analysis. ResultsU-Net-pgs performed best overall, with the highest Dice score (PD: 0.46 {+/-} 0.21; HC: 0.39 {+/-} 0.21), recall (PD: 0.76 {+/-} 0.25; HC: 0.62 {+/-} 0.31), precision (PD: 0.49 {+/-} 0.25; HC: 0.63 {+/-} 0.27), F1 score (PD: 0.54 {+/-} 0.22; HC: 0.56 {+/-} 0.22) and ICC (PD: 0.965; HC: 0.967) and lowest Hausdorff distance (PD: 8.89 {+/-} 3.96; HC: 6.33 {+/-} 2.91). U-Net-pgs achieved the lowest LOGAVD in the PD group (0.31 {+/-} 0.31) whereas BIANCA-LOO with a threshold of 0.9 was lowest in HC (0.27 {+/-} 0.30). U-Net also showed superior performances in all lesion loads for PD and overall across various brain regions in both PD and HC. ConclusionOverall, U-Net-pgs emerged as the best performing automated method, of those we evaluated, for WML segmentation in PD and HC within a dataset collected with various scanner and image acquisition parameters. U-Net-pgs consistently outperformed other automated approaches across lesion loads and brain regions, for most metrics. The accuracy and reliability of U-Net-pgs make it a promising tool for large-scale analyses, facilitating future research investigating WML in PD.