Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering
This work addresses the need for automated PVS segmentation in medical imaging to aid in studying Small Vessel Disease and neuroinflammation, representing an incremental improvement with domain-specific optimization.
The authors tackled the problem of segmenting Perivascular Spaces (PVS) in brain MRI to quantify their burden for understanding neurological diseases, by proposing a method using 3D Frangi filtering optimized with ordered logit models, which achieved a correlation of 0.74 with neuroradiological assessments.
Perivascular Spaces (PVS) are a recently recognised feature of Small Vessel Disease (SVD), also indicating neuroinflammation, and are an important part of the brain's circulation and glymphatic drainage system. Quantitative analysis of PVS on Magnetic Resonance Images (MRI) is important for understanding their relationship with neurological diseases. In this work, we propose a segmentation technique based on the 3D Frangi filtering for extraction of PVS from MRI. Based on prior knowledge from neuroradiological ratings of PVS, we used ordered logit models to optimise Frangi filter parameters in response to the variability in the scanner's parameters and study protocols. We optimized and validated our proposed models on two independent cohorts, a dementia sample (N=20) and patients who previously had mild to moderate stroke (N=48). Results demonstrate the robustness and generalisability of our segmentation method. Segmentation-based PVS burden estimates correlated with neuroradiological assessments (Spearman's $ρ$ = 0.74, p $<$ 0.001), suggesting the great potential of our proposed method