Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images

doi:10.1109/TNB.2023.3276473

	Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images
	Lv, Jinkai 1; Hu, Yuyong 1; Fu, Quanshui 2; Hu, Yuqiang 3; Lv, Lin 4; Yang, Guoqing 2; Li, Jinpeng 5; Zhao, Yi 6,7
	2023-10-01
发表期刊	IEEE TRANSACTIONS ON NANOBIOSCIENCE
ISSN	1536-1241
卷号	22 期号:4 页码:828-835
摘要	Convolution-based methods are increasingly being used in medical image segmentation tasks and have shown good performance, but there are always problems in segmenting edge parts. These methods all have the following challenges: 1) Previous methods do not highlight the relationship between foreground and background in segmented regions, which is helpful for complex segmentation edges, 2) inductive bias of the convolutional layer leads to the fact that the extracted information is mainly the main part of the segmented area, and cannot effectively perceive complex edge changes and the aggregation of small and many segmented areas,3) different regions around the segmentation edge have different reference values for segmentation, and the ordering of these values is more important when the segmentation task is more complex. To address these challenges, we propose the CM-MLP framework on Multi-scale Feature Interaction (MFI) block and Axial Context Relation Encoder (ACRE) block for accurate segmentation of the edge of medical image. In the MFI block, we propose the Cascade Multi-scale MLP (Cascade MLP) to process all local information from the deeper layers of the network simultaneously, using Squeeze and Excitation in Space(SES) to process and redistribute the weights of all windows in Cascade MLP and utilize a cascade multi-scale mechanism to fuse discrete local information gradually. Then, multiple ACRE blocks cooperate with the deep supervision mechanism to gradually explore the boundary relationship between the foreground and the background, and gradually fine-tune the edges of the medical image. The segmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.98%, 96.67%, and 83.83% on three benchmark datasets: CVC-ClinicDB dataset, sub-Kvasir dataset, and our in-house dataset, respectively, which significantly outperform the state-of-the-art method.
关键词	MLP medical image segmentation semantic segmentation
DOI	10.1109/TNB.2023.3276473
收录类别	SCI
语种	英语
资助项目	Research on Intelligent Multimodal Data Integration Algorithm and Its Application in Medical Treatment Foundation[E161080]
WOS研究方向	Biochemistry & Molecular Biology ; Science & Technology - Other Topics
WOS类目	Biochemical Research Methods ; Nanoscience & Nanotechnology
WOS记录号	WOS:001082250700016
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21104
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yang, Guoqing; Li, Jinpeng; Zhao, Yi
作者单位	1.Zhengzhou Univ, Henan Inst Adv Technol, Zhengzhou 450046, Peoples R China 2.Suining Cent Hosp, Suining 629000, Peoples R China 3.Nanchang Univ, Sch Math & Comp Sci, Nanchang 330047, Peoples R China 4.Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 610056, Peoples R China 5.Univ Chinese Acad Sci, Ningbo Inst Life & Hlth Ind, Ningbo 315010, Peoples R China 6.Zhengzhou Univ, Henan Inst Adv Technol, Zhengzhou 450046, Peoples R China 7.Chinese Acad Sci, Inst Comp Technol, Res Ctr Ubiquitous Comp Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Lv, Jinkai,Hu, Yuyong,Fu, Quanshui,et al. Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images[J]. IEEE TRANSACTIONS ON NANOBIOSCIENCE,2023,22(4):828-835.
APA	Lv, Jinkai.,Hu, Yuyong.,Fu, Quanshui.,Hu, Yuqiang.,Lv, Lin.,...&Zhao, Yi.(2023).Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images.IEEE TRANSACTIONS ON NANOBIOSCIENCE,22(4),828-835.
MLA	Lv, Jinkai,et al."Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images".IEEE TRANSACTIONS ON NANOBIOSCIENCE 22.4(2023):828-835.