使用全卷积神经网络对多发性硬化症的脑和病变进行分割：一项大规模研究。
Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study.
机构信息
Department of Diagnostic and Interventional Imaging, The University of Texas Health Science Center at Houston (UTHealth), Houston, TX, USA.
Department of Electrical Engineering, The University of Texas at Tyler, Houston, TX, USA.
出版信息
Mult Scler. 2020 Sep;26(10):1217-1226. doi: 10.1177/1352458519856843. Epub 2019 Jun 13.
OBJECTIVE
To investigate the performance of deep learning (DL) based on fully convolutional neural network (FCNN) in segmenting brain tissues in a large cohort of multiple sclerosis (MS) patients.
METHODS
We developed a FCNN model to segment brain tissues, including T2-hyperintense MS lesions. The training, validation, and testing of FCNN were based on ~1000 magnetic resonance imaging (MRI) datasets acquired on relapsing-remitting MS patients, as a part of a phase 3 randomized clinical trial. Multimodal MRI data (dual-echo, FLAIR, and T1-weighted images) served as input to the network. Expert validated segmentation was used as the target for training the FCNN. We cross-validated our results using the leave-one-center-out approach.
RESULTS
We observed a high average (95% confidence limits) Dice similarity coefficient for all the segmented tissues: 0.95 (0.92-0.98) for white matter, 0.96 (0.93-0.98) for gray matter, 0.99 (0.98-0.99) for cerebrospinal fluid, and 0.82 (0.63-1.0) for T2 lesions. High correlations between the DL segmented tissue volumes and ground truth were observed ( > 0.92 for all tissues). The cross validation showed consistent results across the centers for all tissues.
CONCLUSION
The results from this large-scale study suggest that deep FCNN can automatically segment MS brain tissues, including lesions, with high accuracy.
目的
研究基于全卷积神经网络（FCNN）的深度学习（DL）在对大量多发性硬化症（MS）患者的脑组织进行分割中的性能。
方法
我们开发了一种 FCNN 模型来分割脑组织，包括 T2 高信号 MS 病变。FCNN 的训练、验证和测试基于约 1000 个复发缓解型 MS 患者的磁共振成像（MRI）数据集，作为 3 期随机临床试验的一部分。多模态 MRI 数据（双回波、FLAIR 和 T1 加权图像）作为网络的输入。专家验证的分割被用作训练 FCNN 的目标。我们使用留一中心法进行交叉验证。
结果
我们观察到所有分割组织的平均（95%置信区间）Dice 相似系数都很高：白质为 0.95（0.92-0.98），灰质为 0.96（0.93-0.98），脑脊液为 0.99（0.98-0.99），T2 病变为 0.82（0.63-1.0）。DL 分割组织体积与真实值之间存在高度相关性（所有组织均大于 0.92）。交叉验证结果表明，所有组织在各中心的结果都一致。
结论
这项大规模研究的结果表明，深度 FCNN 可以自动分割 MS 脑组织，包括病变，具有很高的准确性。
Zotero 插件