Multicenter Automated Central Vein Sign Detection Performs as Well as Manual Assessment for the Diagnosis of Multiple Sclerosis

作者：Abigail R. Manning, Vijay Letchuman, Melissa L. Martin, Elaina Gombos, Timothy Robert‐Fitzgerald, Quy Cao, Praneeta Raza, Carly M. O’Donnell, Brian Renner, Lynn Daboul, Paulo Rodrigues, María Jesús Ramos, J. Andrew Derbyshire, Christina Azevedo, Amit Bar‐Or, Eduardo Caverzasi, Peter A. Calabresi, Bruce Cree, Léorah Freeman, Roland G. Henry, Erin E. Longbrake, Jiwon Oh, Nico Papinutto, Daniel Pelletier, Rohini Samudralwar, Suradech Suthiphosuwan, Matthew K. Schindler, Michel Bilello, Jae W. Song, Elias S. Sotirchos, Nancy L. Sicotte, Omar Al‐Louzi, Andrew Solomon, D S Reich, Daniel Ontaneda, Pascal Sati, Russell T. Shinohara, the NAIMS Cooperative · 发表于：American Journal of Neuroradiology · 年份：2024 · DOI：10.3174/ajnr.a8510 · 被引用次数：8 · 研究领域：Multiple Sclerosis Research Studies、Cerebral Venous Sinus Thrombosis、Systemic Lupus Erythematosus Research

BACKGROUND AND PURPOSE: The central vein sign (CVS) is a proposed diagnostic imaging biomarker for multiple sclerosis (MS). The proportion of white matter lesions exhibiting the CVS (CVS+) is higher in patients with MS compared with its radiologic mimics. Evaluation for CVS+ lesions in prior studies has been performed by manual rating, an approach that is time-consuming and has variable interrater reliability. Accurate automated methods would facilitate efficient assessment for CVS. The objective of this study was to compare the performance of an automated CVS detection method with manual rating for the diagnosis of MS. MATERIALS AND METHODS: 3T MRI was acquired in 86 participants undergoing evaluation for MS in a 9-site multicenter study. Participants presented with either typical or atypical clinical syndromes for MS. An automated CVS detection method was employed and compared with manual rating, including total CVS+ proportion and a simplified counting method in which experts visually identified up to 6 CVS+ lesions by using FLAIR* contrast (a voxelwise product of T2 FLAIR and postcontrast T2*-EPI). RESULTS: Automated CVS processing was completed in 79 of 86 participants (91%), of whom 28 (35%) fulfilled the 2017 McDonald criteria at the time of imaging. The area under the receiver operating characteristic curve (AUC) for discrimination between participants with and without MS for the automated CVS approach was 0.78 (95% CI: [0.67,0.88]). This was not significantly differe...