激光与光电子学进展, 2019, 56 (10): 101001, 网络出版: 2019-07-04
一种基于级联卷积网络的三维脑肿瘤精细分割 下载: 1612次
Fine-Granted Segmentation Method for Three-Dimensional Brain Tumors Using Cascaded Convolutional Network
图像处理 三维图像 图像分割 卷积神经网络 磁共振图像 image processing three-dimensional image image segmentation convolutional neural network magnetic resonance image
摘要
提出了一种基于级联的2.5维(2.5D)卷积神经网络。将该任务拆分为脑肿瘤整体分割、肿瘤核分割、增强肿瘤分割三个子任务,并将三个结果合并生成最终结果。在每个子任务中,对三维(3D)图像进行轴向、矢向和冠向的裁取,生成2.5D图像;将2.5D图像输入至所提2.5D V-Net中进行训练;将2.5D分割结果拼接成3D结果,生成不同子任务的分割结果图。结果表明,所提方法对肿瘤整体、肿瘤核和增强肿瘤分割的平均dice值分别可达0.9071、0.8542和0.8140,基本满足临床需要。
Abstract
A cascaded 2.5-dimensional (2.5D) convolutional neural network is proposed. The task is divided into three sub-tasks of whole tumor segmentation, tumor core segmentation and enhancing tumor segmentation, and the results are combined to generate the final result. In each sub-task, the three-dimensional (3D) images are horizontally, coronally and sagittally cropped to generate 2.5D images. The 2.5D images are fed into the proposed 2.5D V-Net for training. The 2.5D segmentation results are concatenated as the 3D results to generate the segmentation results of different sub-tasks. The results show that the average dice scores for the segmentation of whole tumor, tumor core and enhancing tumor by the proposed method are 0.9071, 0.8542, and 0.8140, respectively, which basically meet the clinic need.
褚晶辉, 李晓川, 张佳祺, 吕卫. 一种基于级联卷积网络的三维脑肿瘤精细分割[J]. 激光与光电子学进展, 2019, 56(10): 101001. Jinghui Chu, Xiaochuan Li, Jiaqi Zhang, Wei Lü. Fine-Granted Segmentation Method for Three-Dimensional Brain Tumors Using Cascaded Convolutional Network[J]. Laser & Optoelectronics Progress, 2019, 56(10): 101001.