Rovira Alex, Corral Juan Francisco, Auger Cristina, Valverde Sergi, Vidal-Jordana Angela, Oliver Arnau, de Barros Andrea, Ng Wong Yiken Karelys, Tintoré Mar, Pareto Deborah, Aymerich Francesc Xavier, Montalban Xavier, Lladó Xavier, Alonso Juli
Neuroradiology Section, Department of Radiology (IDI), Vall d'Hebron University Hospital, Barcelona, Spain/Neuroradiology Research Group, Vall d'Hebron Research Institute (VHIR), Barcelona, Spain/Universitat Autònoma de Barcelona, Barcelona, Spain.
Neuroradiology Section, Department of Radiology (IDI), Vall d'Hebron University Hospital, Barcelona, Spain/Neuroradiology Research Group, Vall d'Hebron Research Institute (VHIR), Barcelona, Spain.
Mult Scler. 2022 Jul;28(8):1209-1218. doi: 10.1177/13524585211061339. Epub 2021 Dec 3.
Active (new/enlarging) T2 lesion counts are routinely used in the clinical management of multiple sclerosis. Thus, automated tools able to accurately identify active T2 lesions would be of high interest to neuroradiologists for assisting in their clinical activity.
To compare the accuracy in detecting active T2 lesions and of radiologically active patients based on different visual and automated methods.
One hundred multiple sclerosis patients underwent two magnetic resonance imaging examinations within 12 months. Four approaches were assessed for detecting active T2 lesions: (1) conventional neuroradiological reports; (2) prospective visual analyses performed by an expert; (3) automated unsupervised tool; and (4) supervised convolutional neural network. As a gold standard, a reference outcome was created by the consensus of two observers.
The automated methods detected a higher number of active T2 lesions, and a higher number of active patients, but a higher number of false-positive active patients than visual methods. The convolutional neural network model was more sensitive in detecting active T2 lesions and active patients than the other automated method.
Automated convolutional neural network models show potential as an aid to neuroradiological assessment in clinical practice, although visual supervision of the outcomes is still required.
活动性（新出现/扩大的）T2病变计数在多发性硬化症的临床管理中经常使用。因此，能够准确识别活动性T2病变的自动化工具对于神经放射科医生辅助其临床工作将具有很高的价值。
基于不同的视觉和自动化方法，比较检测活动性T2病变及放射学活动性患者的准确性。
100例多发性硬化症患者在12个月内接受了两次磁共振成像检查。评估了四种检测活动性T2病变的方法：（1）传统神经放射学报告；（2）由专家进行的前瞻性视觉分析；（3）自动化无监督工具；（4）监督式卷积神经网络。作为金标准，由两名观察者的共识创建参考结果。
与视觉方法相比，自动化方法检测到的活动性T2病变数量更多，活动性患者数量更多，但假阳性活动性患者数量也更多。卷积神经网络模型在检测活动性T2病变和活动性患者方面比其他自动化方法更敏感。
自动化卷积神经网络模型在临床实践中显示出作为神经放射学评估辅助手段的潜力，尽管仍需要对结果进行视觉监督。
