[1]李 纬,吴 聪.基于多级残差多尺度的医学图像分割网络[J].湖北工业大学学报,2023,(1):38-42.
　LI Wei,WU Cong.Medical Image Segmentation Network based on Multilevel Residuals and Multi-scales[J].,2023,(1):38-42.
点击复制

基于多级残差多尺度的医学图像分割网络()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2023年第1期
页码:
38-42
栏目:
湖北工业大学学报
出版日期:
2023-03-13

文章信息/Info

Title:
Medical Image Segmentation Network based on Multilevel Residuals and Multi-scales
文章编号:
1003-4684(2023)01-0038-05
作者:
李 纬;  吴 聪
湖北工业大学计算机学院, 湖北 武汉 430068
Author(s):
LI Wei;  WU Cong
School of Computer Science，Hubei Univ. of Tech.，Wuhan 430068,China
关键词:
血管分割;  深度学习;  U-Net;  残差学习;  多尺度
Keywords:
blood vessel segmentation;  deep learning;  u-net;  residual learning; multi-scale
分类号:
TP391
文献标志码:
A
摘要:
针对目前多数U型网络存在编码阶段卷积核尺度单一难以提取变化较大特征以及深层网络难以训练优化的情况，提出一种新的基于多级残差和多尺度的神经网络，利用多级残差使神经网络更易学习，提高网络的深度，使它在模型不退化的情况下拥有更丰富的特征表达能力，提出了了多尺度交叉融合模块，通过不同的感受尺度去提取特征，交叉融合也使得特征信息更加充分的交流和融合。网络在CHASE_DB1数据集上进行测试，并进行数据对比，性能表现优良，特别是ACC达到了0.9744，SP达到了0.9876。提出的网络在增加深度的同时并不影响它的学习过程和表现效果。
Abstract:
At present, in most U-shaped networks, it is difficult to extract features with a single convolution kernel scale in the encoding stage, and it is also difficult to train and optimize the deep network. A new neural network based on multi-level residuals and multi-scale is proposed, which makes the neural network easier to learn, improves the depth of the network, and enables it to have richer feature expression ability, without reducing the performance of the model. In this paper, a multi-scale cross fusion module is proposed, which extracts features through different sensory scales. Cross-fusion also enables feature information to be more fully exchanged and fused. After testing on the data set CHASE _ DB 1, the performance is excellent, especially with ACC being 0.9744, and SP being 0.982. The depth of the proposed network is increased without affecting its learning process and performance.

参考文献/References:

[1] BEN-COHEN A,DIAMANT I,KLANG E,et al.Fully convolutional network for liver segmentation and lesions detection[C].∥Athens,Greece: Springer Verlag,2016:77-85.
[2] DASGUPTA A，SINGH S.A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation[C].∥Melbourne,VIC,Australia:IEEE Computer Society,2017:248-251.
[3] RONNEBERGER O,FISCHER P,BROX T.U-net:convolutional networks for biomedical image segmentation[C].∥Munich,Germany: Springer Verlag,2015:234-241.
[4] KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[5] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].(2014-9-4).[2021-9-20].https:∥arxiv.org/abs/1409.1556.
[6] SZEGEDY C,WEI LIU,YANGQING JIA,et al.Going deeper with convolutions[C].∥Boston,MA,United States: IEEE Computer Society,2015:1-9.
[7] YAN CHENG WU,CHEN H C,SHAO MEI L I,et al.Person re-identification using attribute priori distribution[J].Acta Automatica Sinica,2019,45(5):953-964.
[8] HE KAIMING,ZHANG XIANGYU,REN SHAOQING,et al.Deep residual learning for image rec-ognition[C].∥Las Vegas,NV,United states: IEEE Computer Society,2016:770-778.
[9] NI Z L,BIAN G B,ZHOU X H,et al.RAunet:residual attention U-net for semanticsegmentation of cataract surgical instruments[C].∥Sydney,NSW,Australia: Springer Science and Business Media Deutschland GmbH,2019:139-149.
[10] ZHANG K,SUN M,HAN X,et al.Residual Networks of residual networks: multilevelresidual Networks[J].IEEE Transactions on Circuits and Systems for Video Technolog-y,2018,28(6):1303-1314.
[11] 练秋生,富利鹏,陈书贞,等.基于多尺度残差网络的压缩感知重构算法[J].自动化学报,2019,45(11):2082-2091.
[12] ZHENG K,XIA Z,ZHANG Y,et al.Speech emotion recognition based on multi-level residual convolutional neural networks[J].Engineering Letters,2020,28(2):559-565.
[13] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab: semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IE- EE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[14] WANG W,YU K,HUGONOT J,et al.Recurrent U-net for resource-constrained segmentation[C].∥Seoul,Korea: Institute of Electrical and Electronics Engineers Inc.,United States,2019：2142-2151.
[15] ZHANG B,HUANG S,HU S.Multi-scale neural networks for retinal blood vessels segme-ntation[EB/OL].(2018-4-11).[2021-9-20].https:∥arxiv.org/abs/1804.04206.
[16] JIANG Z,ZHANG H,WANG Y,et al.Retinal blood vessel segmentation using fully convo-lutional network with transfer learning[J].Computerized Medical Imaging and Graphic-s,2018,68(09):1-15.
[17] ZHUANG J.LadderNet:Multi-path networks based on U-Net for medical image segment-ation[EB/OL].(2018-10-17).[2021-9-20].https:∥arxiv.org/abs/1810.07810.
[18] WU Y,XIA Y,SONG Y,et al.Vessel-net:retinal vessel segmentation under multi-path supervision[C].∥Shenzhen,China: Springer Science and Business Media Deutschland GmbH,2019：264-272.
[19] LI X,JIANG Y,LI M,et al.Lightweight attention convolutional neural network for retinal vessel segmentation[J].IEEE Transactions on Industrial Informatics,2020,17(03):1958-1967.
[20] WANG B,WANG S,QIU S,et al.CSU-Net: a context spatial U-net for accurate blo-od vessel segmentation in fundus images[J].IEEE Journal of Biomedical and Health I-nformatics,2020,25(04):1128-1138.

相似文献/References:

[1]杨 帆,陈建峡,郑吟秋,等.基于深度学习的法院信息文本分类[J].湖北工业大学学报,2019,34(4):63.
　YANG Fan,CHEN Jianxia,ZHENG Yingqiu,et al.Research on Classification of Court Information Texts Based on Deep Learning[J].,2019,34(1):63.
[2]龚启文,程 玉,陈建峡,等.基于深度学习的法院命名实体识别模型[J].湖北工业大学学报,2019,34(4):68.
　GONG Qiwen,CHENG Yu,CHEN Jianxia,et al.Research on the Recognition Model of Court Judgment Named Entity Based on Deep Learning[J].,2019,34(1):68.
[3]周星光,靳华中,徐雨东,等.基于多尺度特征的图像描述生成模型[J].湖北工业大学学报,2020,(2):61.
　ZHOU Xingguang,JIN Huazhong,XU Yudong,et al.An Image Description Generation Model Based on Multi-scale[J].,2020,(1):61.
[4]汤青洲,张德津,王墨川,等. SLIC超像素与Inception网络的路面裂缝识别方法[J].湖北工业大学学报,2021,(4):8.
　TANG Qingzhou,ZHANG Dejin,WANG Mochuan,et al. Pavement Crack Detection Method Based on SLIC Superpixel and Inception Network[J].,2021,(1):8.
[5]黄剑锋,王淑青,王年涛,等. 面向无人机巡检的农村输电线螺栓锈蚀检测[J].湖北工业大学学报,2022,(1):54.
　HUANG Jianfeng,WANG Shuqing,WANG Niantao,et al. RuRal Transmission Line Bolt Corrosion Detection Method Oriented to Drone Inspection[J].,2022,(1):54.
[6]顿伟超,王淑青,张鹏飞,等. 基于改进YOLOv4的电力高空作业安全带检测[J].湖北工业大学学报,2022,(5):6.
　DUN Weichao,WANG Shuqing,ZHANG Pengfei,et al. Safety Belt Detection Algorithm for Electric Aerial Work Based on Improved YOLOv4[J].,2022,(1):6.
[7]张鹏飞,王淑青,王年涛,等. 基于改进MobileNetV3的PCB裸板缺陷检测[J].湖北工业大学学报,2023,(1):27.
　ZHANG Pengfei,WANG Shuqing,WANG Niantao,et al. PCB Bare Board Defect Detection Based on Improved MobileNetV3[J].,2023,(1):27.
[8]鲁 濠,王淑青,鲁东林,等. 基于改进YOLOv5的小龙虾品质检测方法[J].湖北工业大学学报,2023,(4):76.
　LU Hao,WANG Shuqing,LU Donglin,et al. Quality Detection Method of Crayfish based on Improved YOLOv5[J].,2023,(1):76.

备注/Memo

备注/Memo:
［收稿日期］ 2021-10-10
［第一作者］ 李 纬（1997-），男，湖北武汉人，湖北工业大学硕士研究生，研究方向为医学图像处理
［通信作者］ 吴 聪（1982-），男，湖北武汉人，工学博士，湖北工业大学副教授，研究方向为医学图像处理
更新日期/Last Update: 2023-03-14