Medical image mis-segmentation region refinement framework based on dynamic graph convolution

作者全名："Liang, Haocheng; Lv, Jia; Wang, Zeyu; Xu, Ximing"

作者地址："[Liang, Haocheng; Lv, Jia; Wang, Zeyu] Chongqing Normal Univ, Coll Comp & Informat Sci, Chongqing 401331, Peoples R China; [Lv, Jia] Chongqing Normal Univ, Natl Ctr Appl Math Chongqing, Chongqing 401331, Peoples R China; [Xu, Ximing] Chongqing Med Univ, Childrens Hosp, Natl Clin Res Ctr Child Hlth & Disorders, Minist Educ,Key Lab Child Dev & Disorders, Chongqing 400014, Peoples R China"

通信作者："Lv, J (通讯作者)，Chongqing Normal Univ, Coll Comp & Informat Sci, Chongqing 401331, Peoples R China.; Xu, XM (通讯作者)，Chongqing Med Univ, Childrens Hosp, Natl Clin Res Ctr Child Hlth & Disorders, Minist Educ,Key Lab Child Dev & Disorders, Chongqing 400014, Peoples R China."

来源：BIOMEDICAL SIGNAL PROCESSING AND CONTROL

ESI学科分类：ENGINEERING

WOS号：WOS:001018592700001

JCR分区：Q1

影响因子：4.9

年份：2023

卷号：86

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Medical image segmentation; Convolutional neural network; Graph convolutional network; Potential mis-segmented region extraction; network; Dynamic graph learning

摘要："In medical image segmentation tasks, it is hard for traditional Convolutional Neural Network (CNN) to capture essential information such as spatial structure and global contextual semantic features since it suffers from a limited receptive field. The deficiency weakens the CNN segmentation performance in the lesion boundary re-gions. To handle the aforementioned problems, a medical image mis-segmentation region refinement framework based on dynamic graph convolution is proposed to refine the boundary and under-segmentation regions. The proposed framework first employs a lightweight dual-path network to detect the boundaries and nearby regions, which can further obtain potentially misclassified pixels from the coarse segmentation results of the CNN. Then, we construct the pixels into the appropriate graphs by CNN-extracted features. Finally, we design a dynamic residual graph convolutional network to reclassify the graph nodes and generate the final refinement results. We chose UNet and its eight representative improved networks as the basic networks and tested them on the COVID, DSB, and BUSI datasets. Experiments demonstrated that the average Dice of our framework is improved by 1.79%, 2.29%, and 2.24%, the average IoU is improved by 2.30%, 3.53%, and 2.39%, and the Se is improved by 5.08%, 4.78%, and 5.31% respectively. The experimental results prove that the proposed framework has the refinement capability to remarkably strengthen the segmentation result of the basic network. Furthermore, the framework has the advantage of high portability and usability, which can be inserted into the end of mainstream medical image segmentation networks as a plug-and-play enhancement block."

基金机构：Chongqing Municipal Education Commission [KJZD-K202200511]; Chongqing Science and Technology Bureau [2022TFII-OFX0044]; Children's Hospital of Chongqing Medical University [NCRCCHD- 2022-HP-01]

基金资助正文：The authors declare the following financial interests/personal re- lationships which may be considered as potential competing interests: Jia Lv reports financial support was provided by Chongqing Municipal Education Commission (KJZD-K202200511) . Jia Lv reports financial support was provided by Chongqing Science and Technology Bureau (2022TFII-OFX0044) . Ximing Xu reports financial support was provided by Children's Hospital of Chongqing Medical University (NCRCCHD- 2022-HP-01) .'