[1]吴 量,付殿臣,程 超.基于 Unet 的多注意力脑肿瘤图像分割算法[J].计算机技术与发展,2021,31(12):85-91.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 015]
　WU Liang,FU Dian-chen,CHENG Chao.Multi-attention Brain Tumor Image Segmentation Algorithm Based on Unet[J].,2021,31(12):85-91.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 015]
点击复制

基于 Unet 的多注意力脑肿瘤图像分割算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年12期
页码:
85-91
栏目:
图形与图像
出版日期:
2021-12-10

文章信息/Info

Title:
Multi-attention Brain Tumor Image Segmentation Algorithm Based on Unet
文章编号:
1673-629X(2021)12-0085-07
作者:
吴 量; 付殿臣; 程 超
长春工业大学 计算机科学与工程学院,吉林 长春 130012
Author(s):
WU Liang; FU Dian-chen; CHENG Chao
School of Computer Science and Engineering,Changchun University of Technology,Changchun 130012,China
关键词:
深度学习; 脑肿瘤图像分割; Unet 网络; 注意力机制; 残差块
Keywords:
deep learning; brain tumor image segmentation; Unet; attention mechanism; Resblock
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 12. 015
摘要:
针对多类型脑肿瘤医学图像分割中上下文信息联系匮乏及人工分割效率、准确率低等问题,提出了一种基于 Unet的脑肿瘤自动分割算法。 首先,在 Unet 模型的基础上引入残差结构( ResBlock),用于加深网络;其次,重新构建 Unet 的解码网络,增加一条并行的膨胀卷积( dalited convolution) 特征提取模块;最后,网络结合改进后的通道和空间多注意力机制,使得网络在提取特征时更加专注某些特征层和空间区域,抑制了某些无效的非病灶区域的冗余特征,进而提高病灶分割的精度。 该文使用医学分割 Dice 评价指标,充分测试算法对多序列脑肿瘤核磁共振(MRI) 医学图像的分割性能。 实验结果表明,改进后的算法在 Complte Dice、Core Dice 和 Enhancing Dice 上分别可达 0. 909,0. 820 和 0. 766。 与 Unet 及其改进的分割算法比较,该算法在参数量与 Unet 相当的情况下获得了更好的分割结果。
Abstract:
In view of the lack of context information connection and the low efficiency and accuracy of artificial segmentation in medical image segmentation of multi-type brain tumors,a automatic segmentation algorithm based on Unet is proposed. Firstly,on the basis of the Unet model,the ResBlock structure is added to deepen the network. Secondly,the decoding network of Unet is reconstructed and a parallel dilation convolution feature extraction module is added. Finally,the network combines the improved channel and spatial multi attention mechanism, which makes the network focus more on some feature layers and spatial regions when extracting features, and suppresses the redundant features of some invalid non lesion regions,so as to improve the accuracy of lesion segmentation. In order to fully test the algorithm’s segmentation performance of multiple sequence brain tumor MRI ( magnetic resonance imaging ) medical images,the indexes of medical segmentation Dice evaluation are used. The experiment shows that the improved algorithm is entitled to 0.909,0. 820 and 0. 766 on Complte Dice,Core Dice and Enhancing Dice respectively. Compared with Unet and its improved segmentation algorithm,it will get a better segmentation result under the condition that the number of parameter quantity is the same as Unet.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(12):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(12):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(12):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(12):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(12):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(12):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(12):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(12):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(12):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(12):7.

更新日期/Last Update: 2021-12-10