In the proposed DLR, a convolutional neural network (CNN) is used. CNN is a representative method used for deep learning, and it has been successfully applied to the field of image segmentation8. Recently, many groups have used CNN for the segmentation of medical images, and it has provided better results than traditional meth- ods9. In glioma segmentation based on MR images, most of the CNN methods were proposed for high-grade gliomas10, 11. Compared with high-grade gliomas, low-grade gliomas are smaller and have lower contrast with the surrounding tissues12. Existing CNN structures would not work well for segmentation of low-grade gliomas. A major architecture adjustment of CNN is therefore essential for both image segmentation and feature extraction. To address the challenging characteristics of low-grade gliomas, we used a modified CNN architecture with 6 convolutional layers and a fully connected layer with 4096 neurons for segmentation. 解释

这段文字讲述了一种名为DLR的分割方法，其中使用了卷积神经网络（CNN），这是一种应用于深度学习的代表性方法，并且已经成功地应用于图像分割领域。最近，许多团队已经将CNN用于医学图像分割，并且相比传统方法，CNN方法提供了更好的结果。然而，对于低级别胶质瘤的分割，由于其大小较小且与周围组织对比度较低，现有的CNN结构无法很好地工作。因此，需要进行主要的架构调整来进行图像分割和特征提取。为了解决低级别胶质瘤的挑战性特征，作者使用了修改后的CNN架构，其中包括6个卷积层和一个有4096个神经元的全连接层用于分割。