当前位置: X-MOL 学术NMR Biomed. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis.
NMR in Biomedicine ( IF 2.9 ) Pub Date : 2020-03-03 , DOI: 10.1002/nbm.4283
Pietro Maggi 1, 2 , Mário João Fartaria 3, 4 , João Jorge 5 , Francesco La Rosa 4, 6 , Martina Absinta 7 , Pascal Sati 7 , Reto Meuli 6 , Renaud Du Pasquier 1 , Daniel S Reich 7 , Meritxell Bach Cuadra 4, 6, 8 , Cristina Granziera 9, 10 , Jonas Richiardi 3, 6 , Tobias Kober 3, 4
Affiliation  

The central vein sign (CVS) is an efficient imaging biomarker for multiple sclerosis (MS) diagnosis, but its application in clinical routine is limited by inter-rater variability and the expenditure of time associated with manual assessment. We describe a deep learning-based prototype for automated assessment of the CVS in white matter MS lesions using data from three different imaging centers. We retrospectively analyzed data from 3 T magnetic resonance images acquired on four scanners from two different vendors, including adults with MS (n = 42), MS mimics (n = 33, encompassing 12 distinct neurological diseases mimicking MS) and uncertain diagnosis (n = 5). Brain white matter lesions were manually segmented on FLAIR* images. Perivenular assessment was performed according to consensus guidelines and used as ground truth, yielding 539 CVS-positive (CVS+ ) and 448 CVS-negative (CVS- ) lesions. A 3D convolutional neural network ("CVSnet") was designed and trained on 47 datasets, keeping 33 for testing. FLAIR* lesion patches of CVS+ /CVS- lesions were used for training and validation (n = 375/298) and for testing (n = 164/150). Performance was evaluated lesion-wise and subject-wise and compared with a state-of-the-art vesselness filtering approach through McNemar's test. The proposed CVSnet approached human performance, with lesion-wise median balanced accuracy of 81%, and subject-wise balanced accuracy of 89% on the validation set, and 91% on the test set. The process of CVS assessment, in previously manually segmented lesions, was ~ 600-fold faster using the proposed CVSnet compared with human visual assessment (test set: 4 seconds vs. 40 minutes). On the validation and test sets, the lesion-wise performance outperformed the vesselness filter method (P < 0.001). The proposed deep learning prototype shows promising performance in differentiating MS from its mimics. Our approach was evaluated using data from different hospitals, enabling larger multicenter trials to evaluate the benefit of introducing the CVS marker into MS diagnostic criteria.

中文翻译:

CVSnet:一种用于多发性硬化症自动中央静脉体征评估的机器学习方法。

中心静脉征 (CVS) 是用于多发性硬化 (MS) 诊断的有效成像生物标志物,但其在临床常规中的应用受到评分者间变异性和与手动评估相关的时间消耗的限制。我们描述了一个基于深度学习的原型,用于使用来自三个不同成像中心的数据自动评估白质 MS 病变中的 CVS。我们回顾性分析了从两个不同供应商的四台扫描仪上获取的 3 T 磁共振图像的数据,包括患有 MS(n = 42)、MS 模拟(n = 33,包括 12 种不同的神经系统疾病模拟 MS)和不确定诊断(n = 5)。在 FLAIR* 图像上手动分割脑白质病变。根据共识指南进行环周评估并用作基本事实,产生 539 个 CVS 阳性 (CVS+ ) 和 448 个 CVS 阴性 (CVS- ) 病灶。在 47 个数据集上设计和训练了一个 3D 卷积神经网络(“CVSnet”),保留 33 个用于测试。CVS+ /CVS- 病灶的 FLAIR* 病灶斑块用于训练和验证 (n = 375/298) 和测试 (n = 164/150)。通过 McNemar 的测试对病变和受试者的性能进行评估,并与最先进的血管过滤方法进行比较。所提出的 CVSnet 接近人类表现,在验证集上的病变中位数平衡准确率为 81%,在主题平衡准确率为 89%,在测试集上为 91%。与人类视觉评估(测试集:4 秒对 40 分钟)相比,使用提议的 CVSnet 在先前手动分割病变中的 CVS 评估过程快了约 600 倍。在验证集和测试集上,病变性能优于血管过滤方法(P < 0.001)。所提出的深度学习原型在将 MS 与其模仿物区分开来方面表现出良好的性能。我们的方法使用来自不同医院的数据进行了评估,使更大的多中心试验能够评估将 CVS 标记物引入 MS 诊断标准的益处。
更新日期:2020-04-22
down
wechat
bug