Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study
Brain and lesion segmentation in multiple sclerosis using fully convolutional neural networks: A large-scale study
复制标题
DOI：
10.1177/1352458519856843
复制
发表时间：
2020-09-01
影响因子：
5.8
通讯作者：
Narayana, Ponnada A.
中科院分区：
文献类型：
--
作者：
Gabr, Refaat E.;Coronado, Ivan;Narayana, Ponnada A.
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）患者脑组织进行分割时的性能。方法：我们开发了一个 FCNN 模型来分割脑组织，包括 T2 高信号 MS 病变。 FCNN 的训练、验证和测试基于从复发缓解型多发性硬化症患者身上采集的约 1000 个磁共振成像 (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。经专家验证的分割被用作训练 FCNN 的目标。我们使用留一中心排除方法交叉验证了我们的结果。结果：我们观察到所有分割组织的 Dice 相似系数平均值较高（95% 置信限）：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)。观察到 DL 分段组织体积与真实值之间的高度相关性（所有组织的 R-2 > 0.92）。交叉验证显示所有组织的各中心结果一致。结论：这项大规模研究的结果表明，深度 FCNN 可以高精度地自动分割 MS 脑组织，包括病变。
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 (R-2 > 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.