摘要
三维脑胶质瘤磁共振成像肿瘤形状各异、边缘模糊,目前大多数基于2D卷积神经网络的分割方法不能很好的分割三维图像。为了能够准确分割出三维图像中的肿瘤部分,提出一种融合多尺度特征信息的3D卷积神经网络脑肿瘤图像分割方法。利用并行的3D空洞卷积提取特征信息,将不同感受野的信息融合。将Dice损失和BCE损失结合,形成一种新的损失函数并配合恒等映射,进一步提高分割精度。在BraTs2020数据集上对模型进行验证,结果表明,该模型分割的全肿瘤区、核心区和增强区的Dice系数分别为89.1%、83.9%和82.6%。在LGG脑部肿瘤图像数据集上对模型进行验证,结果表明,Dice系数达到了93.3%。所提出的分割方法不仅能够精确的分割三维脑胶质瘤图像,而且同样适用于分割二维脑胶质瘤图像。
3 D glioma magnetic resonance imaging has different tumor shapes and blurred edges. The segmentation method based on 2 D Convolutional Neural Network cannot segment the three-dimensional image well. In order to accurately segment the tumor in the three-dimensional image, a 3 D Convolutional Neural Network brain tumor image segmentation method fused with multi-scale feature information is proposed. The feature information is extracted by parallel 3 D dilated convolution, and the information of different receptive fields is fused. The Dice loss and the BCE loss are combined to form a new loss function and cooperate with the identity mapping to further improve the segmentation accuracy. The model was verified on the BraTs2020 data set. The Dice coefficients of the whole tumor area, core area, and enhancement area segmented by the model are 89.1%, 83.9%, 82.6%. The model was verified on the LGG brain tumor image data set, and the Dice coefficient reached 93.3%. The segmentation method can not only accurately segment three-dimensional glioma images, but is also suitable for segmentation of two-dimensional glioma images.
作者
宫浩栋
王育坚
韩静园
GONG Haodong;WANG yujian;HAN jingyuan(School of Information,Bejing Union University,Beijing 100101,China)
出处
《光学技术》
CAS
CSCD
北大核心
2022年第4期472-477,共6页
Optical Technique
基金
国家自然科学基金资助项目(62172045)。
关键词
脑胶质瘤
三维磁共振图像
图像分割
3D卷积神经网络
Brain glioma
three-dimensional magnetic resonance image
image segmentation
3D convolutional neural network
