Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks.
Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks.
复制标题
DOI：
10.1016/j.neuroimage.2018.09.081
复制
发表时间：
2019-01-01
期刊：
影响因子：
5.7
通讯作者：
Cohen-Adad J
中科院分区：
文献类型：
--
作者：
Gros C;De Leener B;Badji A;Maranzano J;Eden D;Dupont SM;Talbott J;Zhuoquiong R;Liu Y;Granberg T;Ouellette R;Tachibana Y;Hori M;Kamiya K;Chougar L;Stawiarz L;Hillert J;Bannier E;Kerbrat A;Edan G;Labauge P;Callot V;Pelletier J;Audoin B;Rasoanandrianina H;Brisset JC;Valsasina P;Rocca MA;Filippi M;Bakshi R;Tauhid S;Prados F;Yiannakas M;Kearney H;Ciccarelli O;Smith S;Treaba CA;Mainero C;Lefeuvre J;Reich DS;Nair G;Auclair V;McLaren DG;Martin AR;Fehlings MG;Vahdat S;Khatibi A;Doyon J;Shepherd T;Charlson E;Narayanan S;Cohen-Adad J
多发性硬化症(MS)患者的脊髓经常受到萎缩和/或病变的影响。从MRI数据中分割脊髓和病变提供了损伤测量，这些测量是多发性硬化症诊断、预后和纵向监测的关键标准。自动化这一操作消除了评分者之间的变异性，并提高了大流量分析管道的效率。由于采集参数和图像伪影具有很大的可变性，因此对多点脊髓数据进行稳健可靠的分割是具有挑战性的。特别是，病变对比度、大小、位置和形状的广泛异质性阻碍了病变的精确描绘。这项研究的目标是开发一个全自动的框架--对图像参数和临床条件的变异性--从多发性硬化症和非多发性硬化症的常规MRI数据中分割脊髓和髓内多发性硬化症病变。这项多点研究包括1042名受试者(459名健康对照，471名多发性硬化症患者和112名其他脊柱疾病患者)的扫描。数据跨越了三种对比(T1加权、T2加权和T2*加权)，共1,943个体积，在分辨率、方向、覆盖范围和临床条件方面具有很大的异质性。本文提出的脊髓和病变自动分割方法是基于两个卷积神经网络(CNN)序列。为了处理脊髓和/或病变体素与体积的其余部分相比非常小的比例，第一个具有2D扩张的卷曲的CNN检测脊髓中心线，然后第二个具有3D卷曲的CNN分割脊髓和/或病变。用Dice Lost对CNN进行独立训练。与人工分割相比，我们基于有线电视新闻网的方法显示出95%的中位DICE比88%的PropSeg(p≤0.05)，这是一种最先进的脊髓分割方法。对于MS数据上的病变分割，我们的框架提供了60%的DICE，15%的−相对体积差，以及83%和77%的病变检测灵敏度和精确度。在这项研究中，我们介绍了一种稳健的方法来分割脊髓和髓内多发性硬化症病变的各种MRI对比。建议的框架是开放源码的，并可在脊髓工具箱中随时获得。
The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework — robust to variability in both image parameters and clinical condition — for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1,042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n=30). Data spanned three contrasts (T1-, T2-, and T2*-weighted) for a total of 1,943 volumes and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p≤0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of −15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.
登录
查看更多内容
影响因子：
5.7
作者：
Carass A;Roy S;Jog A;Cuzzocreo JL;Magrath E;Gherman A;Button J;Nguyen J;Prados F;Sudre CH;Jorge Cardoso M;Cawley N;Ciccarelli O;Wheeler-Kingshott CAM;Ourselin S;Catanese L;Deshpande H;Maurel P;Commowick O;Barillot C;Tomas-Fernandez X;Warfield SK;Vaidya S;Chunduru A;Muthuganapathy R;Krishnamurthi G;Jesson A;Arbel T;Maier O;Handels H;Iheme LO;Unay D;Jain S;Sima DM;Smeets D;Ghafoorian M;Platel B;Birenbaum A;Greenspan H;Bazin PL;Calabresi PA;Crainiceanu CM;Ellingsen LM;Reich DS;Prince JL;Pham DL
通讯作者：
Pham DL
影响因子：
5.8
作者：
Arrambide, Georgina;Rovira, Alex;Tintore, Mar
通讯作者：
Tintore, Mar
影响因子：
5.7
作者：
De Leener, Benjamin;Fonov, Vladimir S.;Cohen-Adad, Julien
通讯作者：
Cohen-Adad, Julien
影响因子：
10.6
作者：
De Leener, Benjamin;Cohen-Adad, Julien;Kadoury, Samuel
通讯作者：
Kadoury, Samuel
影响因子：
5.7
作者：
Chen M;Carass A;Oh J;Nair G;Pham DL;Reich DS;Prince JL
通讯作者：
Prince JL