Manning A R, Letchuman V, Martin M L, Gombos E, Robert-Fitzgerald T, Cao Q, Raza P, O'Donnell C M, Renner B, Daboul L, Rodrigues P, Ramos M, Derbyshire J, Azevedo C, Bar-Or A, Caverzasi E, Calabresi P A, Cree B A C, Freeman L, Henry R G, Longbrake E E, Oh J, Papinutto N, Pelletier D, Samudralwar R D, Suthiphosuwan S, Schindler M K, Bilello M, Song J W, Sotirchos E S, Sicotte N L, Al-Louzi O, Solomon A J, Reich D S, Ontaneda D, Sati P, Shinohara R T
From the Penn Statistics in Imaging and Visualization Center (A.R.M., M.L.M., T.R.-F., Q.C., C.M.O., R.T.S.), Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
Translational Neuroradiology Section (V.L., L.D., O.A.-L., D.S.R., P.S.), National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, Maryland.
AJNR Am J Neuroradiol. 2025 Mar 4;46(3):620-626. doi: 10.3174/ajnr.A8510.
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.
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).
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 different from simplified manual counting methods (select6*) (0.80 [0.69,0.91]) or manual assessment of total CVS+ proportion (0.89 [0.82,0.96]). In a sensitivity analysis excluding 11 participants whose MRI exhibited motion artifact, the AUC for the automated method was 0.81 [0.70,0.91], which was not statistically different from that for select6* (0.79 [0.68,0.92]) or manual assessment of total CVS+ proportion (0.89 [0.81,0.97]).
Automated CVS assessment was comparable to manual CVS scoring for differentiating patients with MS from those with other diagnoses. Large, prospective, multicenter studies utilizing automated methods and enrolling the breadth of disorders referred for suspicion of MS are needed to determine optimal approaches for clinical implementation of an automated CVS detection method.
中央静脉征（CVS）是一种用于多发性硬化症（MS）的诊断性影像生物标志物。与MS的放射学模拟疾病相比，MS患者中表现出CVS（CVS+）的白质病变比例更高。既往研究中对CVS+病变的评估是通过人工评分进行的，这种方法耗时且评分者间的可靠性存在差异。准确的自动化方法将有助于高效评估CVS。本研究的目的是比较自动化CVS检测方法与人工评分在MS诊断中的性能。
在一项9个中心的多中心研究中，对86名接受MS评估的参与者进行了3T磁共振成像（MRI）检查。参与者表现出典型或非典型的MS临床综合征。采用了一种自动化CVS检测方法，并与人工评分进行比较，包括总CVS+比例和一种简化计数方法，即专家通过使用液体衰减反转恢复序列（FLAIR）对比（T2 FLAIR与对比剂后T2回波平面成像的体素乘积）直观识别多达6个CVS+病变。
86名参与者中有79名（91%）完成了自动化CVS处理，其中28名（35%）在成像时符合2017年麦克唐纳标准。自动化CVS方法区分有MS和无MS参与者的受试者工作特征曲线（AUC）下面积为0.78（95%CI：[0.67,0.88]）。这与简化人工计数方法（select6*）（0.80[0.69,0.91]）或人工评估总CVS+比例（0.89[0.82,0.96]）无显著差异。在一项排除11名MRI显示运动伪影的参与者的敏感性分析中，自动化方法的AUC为0.81[0.70,0.91]，与select6*（0.79[0.68,0.92]）或人工评估总CVS+比例（0.89[0.81,0.97]）在统计学上无差异。
在区分MS患者与其他诊断患者方面，自动化CVS评估与人工CVS评分相当。需要开展大型、前瞻性、多中心研究，采用自动化方法并纳入疑似MS的各种疾病患者，以确定自动化CVS检测方法临床应用的最佳途径。
