基于U1-net网络的放疗脑肿瘤靶区分割  

Target segmentation of brain tumor in radiotherapy based on U1-net network

作　　者：张本健 林辉[1] 郭栋 王桂林 胡敏[2] ZHANG Benjian;LIN Hui;GUO Dong;WANG Guilin;HU Min(School of Electronic Science and Applied Physics,Hefei University of Technology,Hefei 230601,China;School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China)

机构地区：[1]合肥工业大学电子科学与应用物理学院,安徽合肥230601 [2]合肥工业大学计算机与信息学院,安徽合肥230601

出　　处：《合肥工业大学学报（自然科学版）》2023年第8期1070-1078,共9页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61672202,U1613217)。

摘　　要：文章基于全卷积神经网络(fully convolutional network,FCN)的U-net网络,并通过对U-net网络的调整,构建适用于脑肿瘤图像分割的U1-net网络。U1-net网络由卷积层、最大池化层、反卷积层和激活函数4个部分组成。通过在公共数据集BRATS 2015上的实验验证了该网络的有效性。实验结果表明,该网络能适应脑肿瘤轮廓取得较好的分割效果,在脑肿瘤的完整肿瘤区、核心肿瘤区、增强肿瘤区的Dice相似系数(Dice similarity coefficient,DSC)分别为0.95、0.85、0.83。This paper is based on the U-net network of the fully convolutional network(FCN),and by adjusting the U-net network,a U1-net network suitable for brain tumor image segmentation is constructed.The U1-net network is composed of four parts:convolution layer,max pooling layer,deconvolution layer and activation function.Through the experimental verification on the public data set BRATS 2015,the validity of the model is verified.The experimental results show that the model can adapt to the contour of brain tumors and achieve a good segmentation effect.In addition,the Dice similarity coefficient(DSC)values of 0.95,0.85 and 0.83 are obtained in the complete tumor region,core tumor region and enhanced tumor region of brain tumors,respectively.

关 键 词：深度学习(DL) 全卷积神经网络(FCN) U1-net网络 BRATS 2015数据集 脑肿瘤分割 

分 类 号：R811.1[医药卫生—放射医学] TP391[医药卫生—临床医学]