Automated Cerebrospinal Fluid Flow Quantification in Hydrocephalus Using Phase‐Contrast Magnetic Resonance Imaging
4 affiliations
- 1CHIMERE Laboratory UA21 INSERM University of Picardie Jules Verne Amiens France
- 2Institut Faire Faces Amiens France
- 3CHU Amiens‐Picardie University Hospital Amiens France
- 4Jules Verne Engineering School Amiens France
Abstract
Quantitative cerebrospinal fluid (CSF) flow analysis with phase‐contrast magnetic resonance imaging depends on segmentation and is affected by operator variability. This cohort method‐comparison study evaluated whether a flow‐aware deep learning (DL) model provides reproducible C2–C3 CSF segmentation and flow quantification compared with repeated manual segmentation. Ten hydrocephalus patients underwent 3‐T phase‐contrast magnetic resonance imaging at C2–C3, with 32 magnitude and phase frames across the cardiac cycle. Three experts and one novice segmented each case twice using semi‐automatic software, generating 80 manual annotations. A pretrained flow‐aware 2D‐UNet generated one fixed automatic segmentation per case. The inference pipeline was deterministic, meaning that repeated processing of the same input with fixed model weights and settings produced identical masks. A multi‐expert reference was defined as the arithmetic mean of the expert measurements. Region of interest (ROI) surface area, peak flow amplitude, and stroke volume were compared using mean difference, Bland–Altman 95% limits of agreement, Lin's concordance correlation coefficient (CCC), and intraclass correlation coefficient (ICC). Expert ICC(1,1) was 0.88–0.97 for surface area, 0.97–1.00 for peak flow amplitude, and 0.97–0.99 for stroke volume; novice values were 0.63, 0.95, and 0.92, respectively. Compared with the multi‐expert reference, model mean differences were −0.42 mm2 for surface area, −0.00 mL/s for peak flow amplitude, and −0.01 mL for stroke volume, with CCC values of 0.50, 0.87, and 0.86. Bland–Altman limits of agreement were −69.12 to 68.27 mm2, −1.47 to 1.46 mL/s, and −0.34 to 0.31 mL. The model provided rapid, deterministic CSF segmentation with small cohort‐level mean differences in peak flow amplitude and stroke volume; however, individual‐level agreement with the flow‐derived multi‐expert reference was lower than for expert and novice segmentations obtained using the semi‐automatic workflow.
Related
- Cerebrospinal fluid surfactant protein-G in neurodegenerative dementia: A comparative study with idiopathic normal-pressure hydrocephalus.
- Cerebrospinal fluid shunt outcomes in patients with idiopathic normal pressure hydrocephalus and an Evans index below 0.3: a prospective study
- VesiScope: A stand-alone tool for the automatic detection, quantification and size analysis of GUVs from phase contrast microscopy images
- An imaging framework for nuclei-based three-dimensional cell quantification in intact tissue using phase-contrast X-ray CT
- MRSIPrep: A Standardized Post-Quantification Framework for Preprocessing Whole-Brain Magnetic Resonance Spectroscopic Imaging
BibTeX
@article{martinez2026automated,
title = {{Automated Cerebrospinal Fluid Flow Quantification in Hydrocephalus Using Phase‐Contrast Magnetic Resonance Imaging}},
author = {Eder Alejandro Rodríguez Martínez and Pan Liu and Kimi Owashi and Antoine Gayet and Olivier Balédent},
journal = {NMR in Biomedicine},
year = {2026},
month = oct,
doi = {10.1002/nbm.70431},
url = {https://u-picardie.hal.science/hal-05845266v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Automated Cerebrospinal Fluid Flow Quantification in Hydrocephalus Using Phase‐Contrast Magnetic Resonance Imaging
AU - Eder Alejandro Rodríguez Martínez
AU - Pan Liu
AU - Kimi Owashi
AU - Antoine Gayet
AU - Olivier Balédent
PY - 2026
DA - 2026/10/26
JO - NMR in Biomedicine
DO - 10.1002/nbm.70431
UR - https://u-picardie.hal.science/hal-05845266v1
AB - Quantitative cerebrospinal fluid (CSF) flow analysis with phase‐contrast magnetic resonance imaging depends on segmentation and is affected by operator variability. This cohort method‐comparison study evaluated whether a flow‐aware deep learning (DL) model provides reproducible C2–C3 CSF segmentation and flow quantification compared with repeated manual segmentation. Ten hydrocephalus patients underwent 3‐T phase‐contrast magnetic resonance imaging at C2–C3, with 32 magnitude and phase frames across the cardiac cycle. Three experts and one novice segmented each case twice using semi‐automatic software, generating 80 manual annotations. A pretrained flow‐aware 2D‐UNet generated one fixed automatic segmentation per case. The inference pipeline was deterministic, meaning that repeated processing of the same input with fixed model weights and settings produced identical masks. A multi‐expert reference was defined as the arithmetic mean of the expert measurements. Region of interest (ROI) surface area, peak flow amplitude, and stroke volume were compared using mean difference, Bland–Altman 95% limits of agreement, Lin's concordance correlation coefficient (CCC), and intraclass correlation coefficient (ICC). Expert ICC(1,1) was 0.88–0.97 for surface area, 0.97–1.00 for peak flow amplitude, and 0.97–0.99 for stroke volume; novice values were 0.63, 0.95, and 0.92, respectively. Compared with the multi‐expert reference, model mean differences were −0.42 mm2 for surface area, −0.00 mL/s for peak flow amplitude, and −0.01 mL for stroke volume, with CCC values of 0.50, 0.87, and 0.86. Bland–Altman limits of agreement were −69.12 to 68.27 mm2, −1.47 to 1.46 mL/s, and −0.34 to 0.31 mL. The model provided rapid, deterministic CSF segmentation with small cohort‐level mean differences in peak flow amplitude and stroke volume; however, individual‐level agreement with the flow‐derived multi‐expert reference was lower than for expert and novice segmentations obtained using the semi‐automatic workflow.
SN - 0952-3480
SN - 1099-1492
ER -