Related Experiment Video
Updated: Feb 23, 2026
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
MR Imaging-based Multimodal Autoidentification of Perivascular Spaces (mMAPS): Automated Morphologic Segmentation of
Erin L Boespflug1, Daniel L Schwartz1, David Lahna1
1From the Department of Neurology (E.L.B., D.L.S., D.L., J.A.K., L.C.S.), Advanced Imaging Research Center (E.L.B., D.L.S., W.R.), Department of Radiology (J.P.), and Department of Anesthesiology and Perioperative Medicine (J.J.I.), Oregon Health & Science University, 3181 SW Sam Jackson Park Rd, Portland, OR 97239-3098.
Abstract:
Purpose To describe a fully automated segmentation method that yields object-based morphologic estimates of enlarged perivascular spaces (ePVSs) in clinical-field-strength (3.0-T) magnetic resonance (MR) imaging data. Materials and Methods In this HIPAA-compliant study, MR imaging data were obtained with a 3.0-T MR imager in research participants without dementia (mean age, 85.3 years; range, 70.4-101.2 years) who had given written informed consent. This method is built on (a) relative normalized white matter, ventricular and cortical signal intensities within T1-weighted, fluid-attenuated inversion recovery, T2-weighted, and proton density data and (b) morphologic (width, volume, linearity) characterization of each resultant cluster. Visual rating was performed by three raters, including one neuroradiologist, after established single-section guidelines. Correlations between visual counts and automated counts, as well session-to-session correlation of counts within each participant, were assessed with the Pearson correlation coefficient r. Results There was a significant correlation between counts by visual raters and automated detection of ePVSs in the same section (r = 0.65, P < .001; r = 0.69, P < .001; and r = 0.54, P < .01 for raters 1, 2, and 3, respectively). With regard to visual ratings and whole-brain count consistency, average visual rating scores were highly correlated with automated detection of total burden volume (r = 0.58, P < .01) and total ePVS number (r = 0.76, P < .01). Morphology of clusters across 28 data sets was consistent with published radiographic estimates of ePVS; mean width of clusters segmented was 3.12 mm (range, 1.7-13.5 mm). Conclusion This MR imaging-based method for multimodal autoidentification of perivascular spaces yields individual whole-brain morphologic characterization of ePVS in clinical MR imaging data and is an important tool in the detailed assessment of these features. © RSNA, 2017 Online supplemental material is available for this article.
Insights
A new automated method accurately estimates enlarged perivascular spaces (ePVSs) using 3.0-T MRI. This tool provides detailed, whole-brain morphologic characterization of ePVSs for improved clinical assessment.
Area of Science:
- Radiology
- Neuroimaging
- Medical Image Analysis
Background:
- Enlarged perivascular spaces (ePVSs) are increasingly recognized in neuroimaging.
- Accurate and automated quantification of ePVSs is crucial for understanding their clinical significance.
- Current methods for ePVS assessment can be time-consuming and subjective.
Purpose of the Study:
- To develop and validate a fully automated segmentation method for estimating object-based morphologic characteristics of ePVSs.
- To assess the performance of this automated method using clinical-field-strength (3.0-T) magnetic resonance (MR) imaging data.
Main Methods:
- Utilized multimodal 3.0-T MR imaging data (T1-weighted, FLAIR, T2-weighted, proton density).
- Developed an automated segmentation approach based on signal intensities and morphologic characterization (width, volume, linearity) of segmented clusters.
- Compared automated counts and morphologic estimates with visual ratings from experienced raters.
Main Results:
- Demonstrated significant correlations between automated ePVS detection and visual ratings (r = 0.65 to 0.54 for section-based counts).
- Highly correlated automated whole-brain burden volume (r = 0.58) and total ePVS number (r = 0.76) with visual assessment.
- Segmented cluster morphology (mean width 3.12 mm) aligned with established radiographic estimates of ePVS.
Conclusions:
- The developed MR imaging-based method enables automated, multimodal identification of perivascular spaces.
- This technique provides individual, whole-brain morphologic characterization of enlarged perivascular spaces (ePVSs) in clinical MR imaging.
- The automated method serves as a valuable tool for detailed assessment of ePVS features in research and potentially clinical settings.
