High resolution automated labeling of the hippocampus and amygdala using a 3D convolutional neural network trained on whole brain 700 μm isotropic 7T MP2RAGE MRI.
High resolution automated labeling of the hippocampus and amygdala using a 3D convolutional neural network trained on whole brain 700 μm isotropic 7T MP2RAGE MRI.
复制标题
DOI：
10.1002/hbm.25348
复制
发表时间：
2021-05
影响因子：
4.8
通讯作者：
Pan J
中科院分区：
文献类型：
--
作者：
Pardoe HR;Antony AR;Hetherington H;Bagić AI;Shepherd TM;Friedman D;Devinsky O;Pan J
使用卷积神经网络(CNN)进行图像标记是传统形态测量技术的一种无模板替代方法。我们在7T采集的全脑700 μm各向同性3D MP2RAGE MRI上训练了一个3D深层细胞神经网络来标记海马区和杏仁体。海马体和杏仁核的人工标记被用来(I)训练预测模型和(Ii)评估模型在应用于新扫描时的性能。我们的分析包括健康对照组和癫痫患者。21名健康对照和16名癫痫患者被纳入研究。我们利用最近开发的DeepMedic软件训练CNN根据手动标记来标记海马体和杏仁核。通过测量基于CNN的标签和手动标签之间的骰子相似系数(DSC)来评估性能。采用留一法交叉验证方案。在健康对照组和癫痫患者中，比较了基于CNN的和手动的对左右海马体和杏仁核体积的估计。这项基于CNN的技术在所有病例中都成功地标记了海马体和杏仁体。海马区平均Dsc=0.88 ± 0.03，杏仁核为0.8 ± 0.06。在我们的样本中，基于CNN的标记与癫痫的诊断无关(p=.91)。在癫痫病例和对照中，基于CNN的体积估计与手动体积估计高度相关。CNN可以在自然亚毫米分辨率的MP2RAGE 7T MRI上标记海马区和杏仁体。我们的发现表明，深度学习技术可以促进高场强、高空间分辨率脑MRI形态计量分析技术的发展。我们训练了一个三维卷积神经网络，在7T采集的全脑700μm各向同性3D MP2RAGE MRI上对海马和杏仁核进行标记。我们的发现表明，深度学习技术可以促进高场强、高空间分辨率脑MRI形态计量分析技术的发展。
Image labeling using convolutional neural networks (CNNs) are a template‐free alternative to traditional morphometric techniques. We trained a 3D deep CNN to label the hippocampus and amygdala on whole brain 700 μm isotropic 3D MP2RAGE MRI acquired at 7T. Manual labels of the hippocampus and amygdala were used to (i) train the predictive model and (ii) evaluate performance of the model when applied to new scans. Healthy controls and individuals with epilepsy were included in our analyses. Twenty‐one healthy controls and sixteen individuals with epilepsy were included in the study. We utilized the recently developed DeepMedic software to train a CNN to label the hippocampus and amygdala based on manual labels. Performance was evaluated by measuring the dice similarity coefficient (DSC) between CNN‐based and manual labels. A leave‐one‐out cross validation scheme was used. CNN‐based and manual volume estimates were compared for the left and right hippocampus and amygdala in healthy controls and epilepsy cases. The CNN‐based technique successfully labeled the hippocampus and amygdala in all cases. Mean DSC = 0.88 ± 0.03 for the hippocampus and 0.8 ± 0.06 for the amygdala. CNN‐based labeling was independent of epilepsy diagnosis in our sample (p = .91). CNN‐based volume estimates were highly correlated with manual volume estimates in epilepsy cases and controls. CNNs can label the hippocampus and amygdala on native sub‐mm resolution MP2RAGE 7T MRI. Our findings suggest deep learning techniques can advance development of morphometric analysis techniques for high field strength, high spatial resolution brain MRI. We trained a 3D convolutional neural network to label the hippocampus and amygdala on whole brain 700 μm isotropic 3D MP2RAGE MRI acquired at 7T. Our findings suggest deep learning techniques can advance development of morphometric analysis techniques for high field strength, high spatial resolution brain MRI.
登录
查看更多内容
影响因子：
5.7
作者：
Henschel L;Conjeti S;Estrada S;Diers K;Fischl B;Reuter M
通讯作者：
Reuter M
影响因子：
5.7
作者：
Marques, Jose P.;Kober, Tobias;Gruetter, Rolf
通讯作者：
Gruetter, Rolf
影响因子：
3.7
作者：
Feldman, Rebecca Emily;Delman, Bradley Neil;Balchandani, Priti
通讯作者：
Balchandani, Priti
影响因子：
5.7
作者：
Chen, Hao;Dou, Qi;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann
影响因子：
5.7
作者：
Morey RA;Petty CM;Xu Y;Hayes JP;Wagner HR 2nd;Lewis DV;LaBar KS;Styner M;McCarthy G
通讯作者：
McCarthy G