基于多任务学习的脑肿瘤MRI分割算法
MRI Segmentation of Brain Tumor Based on the Muti-task learning
投稿时间:2022-12-21  修订日期:2023-03-22
DOI:
中文关键词:  计算机应用技术  脑肿瘤分割  卷积神经网络  磁共振成像  多任务学习
英文关键词:computer application technology  brain tumor segmentation  convolutional neural network  magnetic resonance imaging(MRI)  muti-task learning
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
作者单位邮编
柴文光* 广东工业大学 510006
李文浩 广东工业大学 
闫敬文 汕头大学 
摘要点击次数: 153
全文下载次数: 0
中文摘要:
      针对脑肿瘤MRI (magnetic resonance imaging)分割中样本缺少、类不平衡、小区域分割精度低等问题,本文提出了基于3D No-New U-Net的多尺度多任务深度学习算法TDDU-Net。首先,采用了一个编码器和三个不完全相同解码器的结构;其次,采用逆瓶颈结构设计的ConvXt模块作为解码器的前置处理,克服在部分核心区域解码时高层语义未被充分利用的不足;再次,在最底层编码器和解码器连接处增加广义特征处理模块InConvXt,保证全局特征的准确性,增强网络的稳定性;最后,在保证准确率的情况下,使用深度可分离卷积,减少网络的参数计算量。实验表明,预测分割结果的肿瘤全区域、肿瘤核心区域、增强肿瘤区域Dice相似系数在BraTS18数据集中分别达到了0.907,0.847,0.807。本文方法较其他方法表现出色,能准确分割出较小的肿瘤区域。
英文摘要:
      In order to solve nonnegligible problems in brain tumor MRI segmentation, such as few samples, class imbalance and low accuracy of small districts, this essay proposes a new multi-scale and multitask deep-learning algorithm called TDDU-Net based on 3D No-New U-Net. Firstly, this paper applied the structure with an encoder and three different decoders to the network. Next, the ConvXt module is a custom-designed pre-processor set in front of the original decoders in order to overcome the underutilization of high-level semantics in some core region. Then, InConvXt is a generalized feature processing module set at the bottom layer between the encoder and decoder to ensure the accuracy of the generalized features and enhance the stability of the network. Finally, the deepwise convolution is used to reduce the amount of the network parameter at the appropriate location while ensuring accuracy. The experiments show that the dice similarity coefficients of the predicted segmentation in the BraTS18 dataset reaching 0.907, 0.847, 0.807 in the whole tumor region, the core tumor region and the enhanced tumor region. The method performs better and makes fewer mistakes than others, which is helpful in segmenting the smaller tumor area in MRI.
    下载PDF阅读器
关闭

版权所有:《光电子·激光》编辑部  津ICP备12008651号-1
主管单位:天津市教育委员会 主办单位:天津理工大学 地址:中国天津市西青区宾水西道391号
技术支持:北京勤云科技发展有限公司