基于长短期记忆网络（LSTM）的儿童脑磁共振成像（MRI）脑龄估计
BRAIN AGE ESTIMATION USING LSTM ON CHILDREN'S BRAIN MRI.
作者信息
He Sheng, Gollub Randy L, Murphy Shawn N, Perez Juan David, Prabhu Sanjay, Pienaar Rudolph, Robertson Richard L, Grant P Ellen, Ou Yangming
机构信息
Boston Children's Hospital, Harvard Medical School, Boston, USA.
Massachusetts General Hospital, Harvard Medical School, Boston, USA.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:420-423. doi: 10.1109/isbi45749.2020.9098356. Epub 2020 May 22.
Brain age prediction based on children's brain MRI is an important biomarker for brain health and brain development analysis. In this paper, we consider the 3D brain MRI volume as a sequence of 2D images and propose a new framework using the recurrent neural network for brain age estimation. The proposed method is named as 2D-ResNet18+Long short-term memory (LSTM), which consists of four parts: 2D ResNet18 for feature extraction on 2D images, a pooling layer for feature reduction over the sequences, an LSTM layer, and a final regression layer. We apply the proposed method on a public multisite NIH-PD dataset and evaluate generalization on a second multisite dataset, which shows that the proposed 2D-ResNet18+LSTM method provides better results than traditional 3D based neural network for brain age estimation.
基于儿童脑部磁共振成像（MRI）的脑龄预测是脑健康和脑发育分析的重要生物标志物。在本文中，我们将三维脑部MRI体积视为二维图像序列，并提出了一种使用递归神经网络进行脑龄估计的新框架。所提出的方法被命名为2D-ResNet18+长短期记忆网络（LSTM），它由四个部分组成：用于二维图像特征提取的2D ResNet18、用于序列特征降维的池化层、一个LSTM层和一个最终回归层。我们将所提出的方法应用于一个公共的多站点NIH-PD数据集，并在第二个多站点数据集上评估其泛化能力，结果表明所提出的2D-ResNet18+LSTM方法在脑龄估计方面比传统的基于三维的神经网络提供了更好的结果。
Zotero 插件