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

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 foregroun...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on nanobioscience Ročník 22; číslo 4; s. 1
Hlavní autori:	Lv, Jinkai, Hu, Yuyong, Fu, Quanshui, Hu, Yuqiang, Lv, Lin, Yang, Guoqing, Li, Jinpeng, Zhao, Yi
Médium:	Magazine Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 01.10.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Coders Datasets Decoding Feature extraction Image edge detection Image processing Image segmentation Information processing medical image segmentation Medical imaging MLP Object segmentation semantic segmentation Source code STEM Task analysis
ISSN:	1536-1241, 1558-2639, 1558-2639
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	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) The 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 super-vision 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. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP.
AbstractList	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. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP.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. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP. 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. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP . 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) The 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 super-vision 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. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP.
Author	Lv, Lin Hu, Yuqiang Yang, Guoqing Fu, Quanshui Li, Jinpeng Lv, Jinkai Zhao, Yi Hu, Yuyong
Author_xml	– sequence: 1 givenname: Jinkai surname: Lv fullname: Lv, Jinkai organization: Henan Institute of Advanced Technology, Zhengzhou University, Zhengzhou, China – sequence: 2 givenname: Yuyong surname: Hu fullname: Hu, Yuyong organization: Henan Institute of Advanced Technology, Zhengzhou University, Zhengzhou, China – sequence: 3 givenname: Quanshui surname: Fu fullname: Fu, Quanshui organization: Suining Central Hospital, Suining, China – sequence: 4 givenname: Yuqiang surname: Hu fullname: Hu, Yuqiang organization: School of Mathematics and Computer Sciences, NanChang University, Nanchang, China – sequence: 5 givenname: Lin surname: Lv fullname: Lv, Lin organization: School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 6 givenname: Guoqing surname: Yang fullname: Yang, Guoqing organization: Suining Central Hospital, Suining, China – sequence: 7 givenname: Jinpeng orcidid: 0000-0001-8701-2642 surname: Li fullname: Li, Jinpeng organization: Ningbo Institute of Life and Health Industry, University of Chinese Academy of Sciences, Ningbo, China – sequence: 8 givenname: Yi surname: Zhao fullname: Zhao, Yi organization: Henan Institute of Advanced Technology, Zhengzhou University, Zhengzhou, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37186536$$D View this record in MEDLINE/PubMed
BookMark	eNp9kc1P3DAQxa1qUWGBOweEIvXSSxZ_xbG5wYptkZYPCeg1cpzxKiiJF9s59L-vo91WFQdO8zT-vRlr3hzNBjcAQmcELwjB6vLl4WZBMWULRkvBS_YFHZGikDkVTM0mzUROKCeHaB7CG8akFIX6ig5ZSaRIj0fo19oZ3WUr0HH0kN3rGMGHq2ypg9FNaoxdbPOku6TXT5l1PrttNpA9w6aHIerYuiFzNruHpp0m3fV6A-EEHVjdBTjd12P0urp9Wf7M148_7pbX69wwLmOusOSNtkxLa2whaUMMZ1aYojSaEYwp1rWqhWQ1kwCcYlVTyQVhqgRLaMOO0ffd3K137yOEWPVtMNB1egA3hopKwguqsOAJ_fYBfXOjH9LvElVSXihaTNTFnhrrHppq69te-9_V34slAO8A410IHuw_hOBqCqVKoVRTKNU-lGQRHyym3R0uet12nxnPd8YWAP7bkyItBWN_AINilfI
CODEN	ITMCEL
CitedBy_id	crossref_primary_10_1016_j_compbiomed_2024_108939 crossref_primary_10_1016_j_eswa_2024_125874 crossref_primary_10_1002_ima_23199 crossref_primary_10_1016_j_patcog_2025_112384 crossref_primary_10_1016_j_compbiomed_2024_107955 crossref_primary_10_1016_j_media_2025_103551 crossref_primary_10_1016_j_bbe_2024_04_001
Cites_doi	10.1007/978-3-030-59719-1_36 10.1007/978-3-030-37734-2_37 10.1007/978-3-030-58558-7_29 10.1109/CVPR52688.2022.00307 10.1109/TMI.2019.2959609 10.1109/3DV.2016.79 10.1007/978-3-030-00934-2_99 10.1109/TMI.2015.2487997 10.1016/j.knosys.2019.04.025 10.1109/BIBM55620.2022.9995348 10.1109/ICCV.2017.89 10.1038/s41592-019-0612-7 10.1007/978-3-030-59725-2_26 10.1109/CVPR52688.2022.00568 10.1007/978-3-030-87193-2_22 10.1016/j.patrec.2017.11.005 10.1109/TMI.2018.2845918 10.1109/ITME.2018.00080 10.1016/j.media.2021.102002 10.1109/CVPR52688.2022.00066 10.1109/ICASSP40776.2020.9053405 10.1109/TPAMI.2022.3145427 10.1007/978-3-030-59710-8_8 10.1109/ICCV48922.2021.00389 10.1109/CVPR.2018.00745
ContentType	Magazine Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
DOI	10.1109/TNB.2023.3276473
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Materials Research Database PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	1558-2639
EndPage	1
ExternalDocumentID	37186536 10_1109_TNB_2023_3276473 10124763
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Research on Intelligent Multimodal Data Integration Algorithm and Its Application in Medical Treatment Foundation grantid: E161080
GroupedDBID	--- -~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACPRK AENEX AFRAH AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS 5VS AAYXX AETIX AGSQL AIBXA CITATION EJD H~9 NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
ID	FETCH-LOGICAL-c348t-9084daf3a8fcf582d1c43f6c57ca310020ab9b683b38ee4209b28461397ef12d3
IEDL.DBID	RIE
ISICitedReferencesCount	7
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001082250700016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1241 1558-2639
IngestDate	Sat Sep 27 18:08:08 EDT 2025 Mon Jun 30 10:11:14 EDT 2025 Thu Jan 02 22:51:41 EST 2025 Tue Nov 18 22:32:08 EST 2025 Sat Nov 29 03:31:11 EST 2025 Wed Aug 27 02:56:18 EDT 2025
IsPeerReviewed	false
IsScholarly	false
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c348t-9084daf3a8fcf582d1c43f6c57ca310020ab9b683b38ee4209b28461397ef12d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-8701-2642
PMID	37186536
PQID	2872459254
PQPubID	85413
PageCount	1
ParticipantIDs	crossref_citationtrail_10_1109_TNB_2023_3276473 pubmed_primary_37186536 proquest_miscellaneous_2814529064 proquest_journals_2872459254 ieee_primary_10124763 crossref_primary_10_1109_TNB_2023_3276473
PublicationCentury	2000
PublicationDate	2023-10-01
PublicationDateYYYYMMDD	2023-10-01
PublicationDate_xml	– month: 10 year: 2023 text: 2023-10-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on nanobioscience
PublicationTitleAbbrev	TNB
PublicationTitleAlternate	IEEE Trans Nanobioscience
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref12 liu (ref14) 2021; 34 ref11 ref33 jha (ref34) 2020 ref10 ref32 ref2 ref1 ref17 ref16 ref19 ref18 oktay (ref6) 2018 maria jose valanarasu (ref31) 2022 ref24 ref26 ref25 ref20 ref22 chen (ref15) 2021 ref28 ref27 ref29 lou (ref30) 2021 ref8 ref7 ref4 ref3 ronneberger (ref23) 2015 ref5 tolstikhin (ref13) 2021; 34 zhang (ref35) 2019; 32 dosovitskiy (ref21) 2020 çiçek (ref9) 2016
References_xml	– ident: ref12 doi: 10.1007/978-3-030-59719-1_36 – year: 2021 ident: ref15 article-title: CycleMLP: A MLP-like architecture for dense prediction publication-title: arXiv 2107 10224 – start-page: 451 year: 2020 ident: ref34 article-title: Kvasir-SEG: A segmented polyp dataset publication-title: Multimedia Modeling doi: 10.1007/978-3-030-37734-2_37 – ident: ref20 doi: 10.1007/978-3-030-58558-7_29 – volume: 34 start-page: 9204 year: 2021 ident: ref14 article-title: Pay attention to MLPs publication-title: Advances in neural information processing systems – ident: ref16 doi: 10.1109/CVPR52688.2022.00307 – ident: ref4 doi: 10.1109/TMI.2019.2959609 – ident: ref10 doi: 10.1109/3DV.2016.79 – ident: ref11 doi: 10.1007/978-3-030-00934-2_99 – ident: ref33 doi: 10.1109/TMI.2015.2487997 – ident: ref24 doi: 10.1016/j.knosys.2019.04.025 – ident: ref22 doi: 10.1109/BIBM55620.2022.9995348 – ident: ref25 doi: 10.1109/ICCV.2017.89 – ident: ref2 doi: 10.1038/s41592-019-0612-7 – ident: ref29 doi: 10.1007/978-3-030-59725-2_26 – year: 2021 ident: ref30 article-title: CaraNet: Context axial reverse attention network for segmentation of small medical objects publication-title: arXiv 2108 07368 – ident: ref18 doi: 10.1109/CVPR52688.2022.00568 – year: 2022 ident: ref31 article-title: UNeXt: MLP-based rapid medical image segmentation network publication-title: arXiv 2203 04967 – ident: ref28 doi: 10.1007/978-3-030-87193-2_22 – ident: ref1 doi: 10.1016/j.patrec.2017.11.005 – ident: ref7 doi: 10.1109/TMI.2018.2845918 – ident: ref5 doi: 10.1109/ITME.2018.00080 – start-page: 424 year: 2016 ident: ref9 article-title: 3D U-Net: Learning dense volumetric segmentation from sparse annotation publication-title: Medical Image Computing and Computer-Assisted Intervention-MICCAI – ident: ref3 doi: 10.1016/j.media.2021.102002 – year: 2018 ident: ref6 article-title: Attention U-Net: Learning where to look for the pancreas publication-title: arXiv 1804 03999 – volume: 32 year: 2019 ident: ref35 article-title: Lookahead optimizer: K steps forward, 1 step back publication-title: Advances in neural information processing systems – start-page: 234 year: 2015 ident: ref23 article-title: U-Net: Convolutional networks for biomedical image segmentation publication-title: Medical Image Computing and Computer-Assisted Intervention-MICCAI – ident: ref19 doi: 10.1109/CVPR52688.2022.00066 – year: 2020 ident: ref21 article-title: An image is worth 16×16 words: Transformers for image recognition at scale publication-title: arXiv 2010 11929 – ident: ref8 doi: 10.1109/ICASSP40776.2020.9053405 – ident: ref17 doi: 10.1109/TPAMI.2022.3145427 – ident: ref27 doi: 10.1007/978-3-030-59710-8_8 – volume: 34 start-page: 24261 year: 2021 ident: ref13 article-title: MLP-Mixer: An all-MLP architecture for vision publication-title: Advances in neural information processing systems – ident: ref32 doi: 10.1109/ICCV48922.2021.00389 – ident: ref26 doi: 10.1109/CVPR.2018.00745
SSID	ssj0017659
Score	1.2444074
Snippet	Convolution-based methods are increasingly being used in medical image segmentation tasks and have shown good performance, but there are always problems in...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1
SubjectTerms	Coders Datasets Decoding Feature extraction Image edge detection Image processing Image segmentation Information processing medical image segmentation Medical imaging MLP Object segmentation semantic segmentation Source code STEM Task analysis
Title	Local Feature Matters: Cascade Multi-scale MLP for Edge Segmentation of Medical Images
URI	https://ieeexplore.ieee.org/document/10124763 https://www.ncbi.nlm.nih.gov/pubmed/37186536 https://www.proquest.com/docview/2872459254 https://www.proquest.com/docview/2814529064
Volume	22
WOSCitedRecordID	wos001082250700016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dSxwxEB9ULPTJam3dViWFvvRh7_Y2uXz4pqK0cB5Cbbm3JckmIuie3EfB_96Z7N5RHyz0LbDZ3TAfmclMZn4AX3HP586hphlbKArd2NxpijY5tN3cS6ddKhQeqfFYTybmuitWT7UwIYR0-Sz0aJhy-fXULylU1qdeVAIVYhM2lZJtsdY6ZaBkQkZDDSZgGTFY5SQL078Zn_UIJrzHSyWF4i9sUAJVed2_THbmcuc_V_gOdlYNotlpKwK7sBGaPXjTYkw-vYffI7JWjFy95Sywq7af5gk7t3O6Gs9SBW6O43scj64ZOrHsor4N7Ge4fegKkxo2jaxL6bAfD7gFzffh1-XFzfn3vANTyD0XepGbQovaRm519HGoy3rgBY_SD5W3FOQvC-uMk5o7rkMQZWEcWi5JDmKIg7LmH2CrmTbhAJiKpg7ol5V-GNCfiS7GUJraaGu5EbLIoL8ib-W7TuMEeHFfpRNHYSpkSEUMqTqGZPBt_cZj22XjH3P3ie5_zWtJnsHhioVVp4fzCs-DpRgaPAVn8GX9GDWI0iK2CdMlzRlQ9hl9sww-tqxff5yj6ZYoUZ9e-elneEtra2_3HcLWYrYMR7Dt_yzu5rNjFNOJPk5i-gy5ZOAN
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BAcGpPAoNFDASFw7ZzcZOYnODqlUr0lUlFtRbZDvjCqnNVvtA4t8z42RXcCgSN0txEmvG4xnP6wN4T2e-dI4kzdisYteNTZ1mb5Mj3S196bSLhcJ1NZ3qiwtzPhSrx1oYRIzJZzjiYYzlt3O_ZlfZmHtRKRKIu3CvUCrP-nKtbdCgKiM2GskwQ8uoySYqmZnxbPp5xEDhI5lXparkX1oowqrcbmFGTXO8-59rfAy7mxbR4lO_CZ7AHeyewoMeZfLXM_hes74SbOytFyjO-o6aH8WhXXJyvIg1uCmNr2hcnwsyY8VRe4niK15eD6VJnZgHMQR1xOk1HULLPfh2fDQ7PEkHOIXUS6VXqcm0am2QVgcfCp23E69kKH1Rectu_jyzzrhSSyc1IpHXONJdJZuIGCZ5K5_DTjfvcB9EFUyLZJnlvkCyaIILAXPTGm2tNKrMEhhvyNv4odc4Q15cNfHOkZmGGNIwQ5qBIQl82L5x0_fZ-MfcPab7H_N6kidwsGFhM0jisqEbYa4KQ_fgBN5tH5MMcWDEdjhf85wJx5_JOkvgRc_67cclKe-SdtTLW376Fh6ezM7qpj6dfnkFj3idfa7fAeysFmt8Dff9z9WP5eJN3Ky_AUF74mw
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Local+Feature+Matters%3A+Cascade+Multi-Scale+MLP+for+Edge+Segmentation+of+Medical+Images&rft.jtitle=IEEE+transactions+on+nanobioscience&rft.au=Lv%2C+Jinkai&rft.au=Hu%2C+Yuyong&rft.au=Fu%2C+Quanshui&rft.au=Hu%2C+Yuqiang&rft.date=2023-10-01&rft.issn=1536-1241&rft.eissn=1558-2639&rft.volume=22&rft.issue=4&rft.spage=828&rft.epage=835&rft_id=info:doi/10.1109%2FTNB.2023.3276473&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TNB_2023_3276473
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1241&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1241&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1241&client=summon