No Cover Image

Journal article 54 views 3 downloads

MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation

Shaoqiang Wang Orcid Logo, Zhongran Liu Orcid Logo, Guiling Shi, Chengye Li, Linhao Zhang, Tiyao Liu, Yawu Zhao, Yuchen Wang, Qiang Li, Cheng Cheng Orcid Logo

IET Systems Biology, Volume: 20, Issue: 1

Swansea University Author: Cheng Cheng Orcid Logo

  • 71133.VoR.pdf

    PDF | Version of Record

    © 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License.

    Download (1.23MB)

Check full text

DOI (Published version): 10.1049/syb2.70044

Abstract

The automated segmentation of thyroid nodules from ultrasound images holds significant value in clinical diagnosis and treatment. However, achieving precise segmentation remains a substantial challenge due to issues such as blurred nodule boundaries, variable scales, image noise, and inaccurate anno...

Full description

Published in: IET Systems Biology
ISSN: 1751-8849 1751-8857
Published: Institution of Engineering and Technology (IET) 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71133
first_indexed 2025-12-11T16:01:33Z
last_indexed 2026-02-28T05:40:53Z
id cronfa71133
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-02-27T16:19:30.6745163</datestamp><bib-version>v2</bib-version><id>71133</id><entry>2025-12-11</entry><title>MFS&#x2010;Unet: A Multi&#x2010;Path Vision Mamba Network for Precise Thyroid Nodule Segmentation</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-12-11</date><deptcode>MACS</deptcode><abstract>The automated segmentation of thyroid nodules from ultrasound images holds significant value in clinical diagnosis and treatment. However, achieving precise segmentation remains a substantial challenge due to issues such as blurred nodule boundaries, variable scales, image noise, and inaccurate annotations. To address these difficulties, this paper proposes a novel medical image segmentation network named MFS-Unet. The network introduces three innovative modules to enhance segmentation performance. First, we designed the multi-path vision mamba (MPV) module, which leverages the advantages of state space models (SSMs) to efficiently capture global contextual information and multi-scale features with linear computational complexity, effectively addressing the problem of significant variations in nodule size. Second, a feature gating (FG) module is deployed in the skip connections between the encoder and decoder. Through an attention mechanism, it dynamically screens and enhances features transmitted from the encoder, suppressing background noise and reinforcing key boundary information of the nodules. Finally, we propose a supervised label rectification (SLR) module, aimed at proactively handling the prevalent issue of label noise in training data. By dynamically adjusting loss weights during training, it guides the model to learn more robust feature representations. We conducted extensive experiments on three public thyroid ultrasound datasets: DDTI, TG3K, and TN3K. The results demonstrate that MFS-Unet achieves superior performance across all evaluation metrics compared with various state-of-the-art segmentation methods, proving its effectiveness and significant potential for precise thyroid nodule segmentation in complex ultrasound environments.</abstract><type>Journal Article</type><journal>IET Systems Biology</journal><volume>20</volume><journalNumber>1</journalNumber><paginationStart/><paginationEnd/><publisher>Institution of Engineering and Technology (IET)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1751-8849</issnPrint><issnElectronic>1751-8857</issnElectronic><keywords>Medical Image Segmentation, Thyroid Nodule, State Space Model, Label Noise</keywords><publishedDay>5</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-02-05</publishedDate><doi>10.1049/syb2.70044</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Authors are funded by UKRI Grant EP/W020408/1 and Grant RS718 through Doctoral Training Centre at Swansea University.</funders><projectreference/><lastEdited>2026-02-27T16:19:30.6745163</lastEdited><Created>2025-12-11T14:52:26.6683730</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Shaoqiang</firstname><surname>Wang</surname><orcid>0000-0002-7539-5970</orcid><order>1</order></author><author><firstname>Zhongran</firstname><surname>Liu</surname><orcid>0009-0001-3180-3370</orcid><order>2</order></author><author><firstname>Guiling</firstname><surname>Shi</surname><order>3</order></author><author><firstname>Chengye</firstname><surname>Li</surname><order>4</order></author><author><firstname>Linhao</firstname><surname>Zhang</surname><order>5</order></author><author><firstname>Tiyao</firstname><surname>Liu</surname><order>6</order></author><author><firstname>Yawu</firstname><surname>Zhao</surname><order>7</order></author><author><firstname>Yuchen</firstname><surname>Wang</surname><order>8</order></author><author><firstname>Qiang</firstname><surname>Li</surname><order>9</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>10</order></author></authors><documents><document><filename>71133__36328__f7f7cfd3af734647b1717e47171735f8.pdf</filename><originalFilename>71133.VoR.pdf</originalFilename><uploaded>2026-02-27T16:16:53.5323668</uploaded><type>Output</type><contentLength>1294329</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-02-27T16:19:30.6745163 v2 71133 2025-12-11 MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2025-12-11 MACS The automated segmentation of thyroid nodules from ultrasound images holds significant value in clinical diagnosis and treatment. However, achieving precise segmentation remains a substantial challenge due to issues such as blurred nodule boundaries, variable scales, image noise, and inaccurate annotations. To address these difficulties, this paper proposes a novel medical image segmentation network named MFS-Unet. The network introduces three innovative modules to enhance segmentation performance. First, we designed the multi-path vision mamba (MPV) module, which leverages the advantages of state space models (SSMs) to efficiently capture global contextual information and multi-scale features with linear computational complexity, effectively addressing the problem of significant variations in nodule size. Second, a feature gating (FG) module is deployed in the skip connections between the encoder and decoder. Through an attention mechanism, it dynamically screens and enhances features transmitted from the encoder, suppressing background noise and reinforcing key boundary information of the nodules. Finally, we propose a supervised label rectification (SLR) module, aimed at proactively handling the prevalent issue of label noise in training data. By dynamically adjusting loss weights during training, it guides the model to learn more robust feature representations. We conducted extensive experiments on three public thyroid ultrasound datasets: DDTI, TG3K, and TN3K. The results demonstrate that MFS-Unet achieves superior performance across all evaluation metrics compared with various state-of-the-art segmentation methods, proving its effectiveness and significant potential for precise thyroid nodule segmentation in complex ultrasound environments. Journal Article IET Systems Biology 20 1 Institution of Engineering and Technology (IET) 1751-8849 1751-8857 Medical Image Segmentation, Thyroid Nodule, State Space Model, Label Noise 5 2 2026 2026-02-05 10.1049/syb2.70044 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University SU Library paid the OA fee (TA Institutional Deal) Authors are funded by UKRI Grant EP/W020408/1 and Grant RS718 through Doctoral Training Centre at Swansea University. 2026-02-27T16:19:30.6745163 2025-12-11T14:52:26.6683730 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Shaoqiang Wang 0000-0002-7539-5970 1 Zhongran Liu 0009-0001-3180-3370 2 Guiling Shi 3 Chengye Li 4 Linhao Zhang 5 Tiyao Liu 6 Yawu Zhao 7 Yuchen Wang 8 Qiang Li 9 Cheng Cheng 0000-0003-0371-9646 10 71133__36328__f7f7cfd3af734647b1717e47171735f8.pdf 71133.VoR.pdf 2026-02-27T16:16:53.5323668 Output 1294329 application/pdf Version of Record true © 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License. true eng http://creativecommons.org/licenses/by/4.0/
title MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
spellingShingle MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
Cheng Cheng
title_short MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
title_full MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
title_fullStr MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
title_full_unstemmed MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
title_sort MFS‐Unet: A Multi‐Path Vision Mamba Network for Precise Thyroid Nodule Segmentation
author_id_str_mv 11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv 11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author Cheng Cheng
author2 Shaoqiang Wang
Zhongran Liu
Guiling Shi
Chengye Li
Linhao Zhang
Tiyao Liu
Yawu Zhao
Yuchen Wang
Qiang Li
Cheng Cheng
format Journal article
container_title IET Systems Biology
container_volume 20
container_issue 1
publishDate 2026
institution Swansea University
issn 1751-8849
1751-8857
doi_str_mv 10.1049/syb2.70044
publisher Institution of Engineering and Technology (IET)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description The automated segmentation of thyroid nodules from ultrasound images holds significant value in clinical diagnosis and treatment. However, achieving precise segmentation remains a substantial challenge due to issues such as blurred nodule boundaries, variable scales, image noise, and inaccurate annotations. To address these difficulties, this paper proposes a novel medical image segmentation network named MFS-Unet. The network introduces three innovative modules to enhance segmentation performance. First, we designed the multi-path vision mamba (MPV) module, which leverages the advantages of state space models (SSMs) to efficiently capture global contextual information and multi-scale features with linear computational complexity, effectively addressing the problem of significant variations in nodule size. Second, a feature gating (FG) module is deployed in the skip connections between the encoder and decoder. Through an attention mechanism, it dynamically screens and enhances features transmitted from the encoder, suppressing background noise and reinforcing key boundary information of the nodules. Finally, we propose a supervised label rectification (SLR) module, aimed at proactively handling the prevalent issue of label noise in training data. By dynamically adjusting loss weights during training, it guides the model to learn more robust feature representations. We conducted extensive experiments on three public thyroid ultrasound datasets: DDTI, TG3K, and TN3K. The results demonstrate that MFS-Unet achieves superior performance across all evaluation metrics compared with various state-of-the-art segmentation methods, proving its effectiveness and significant potential for precise thyroid nodule segmentation in complex ultrasound environments.
published_date 2026-02-05T05:29:00Z
_version_ 1858617464646008832
score 11.098272

Similar Items