Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies

COSTA, SARAH; Eshkiki, Hassan; Caraffini, Fabio; George, Christopher

doi:10.1007/978-3-032-00656-1_26

Conference Paper/Proceeding/Abstract 737 views 143 downloads

Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies

SARAH COSTA, Hassan Eshkiki

, Fabio Caraffini

, Christopher George

Lecture Notes in Computer Science, Volume: 16039, Pages: 351 - 365

Swansea University Authors: SARAH COSTA, Hassan Eshkiki , Fabio Caraffini , Christopher George

PDF | Accepted Manuscript

Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (4.67MB)

Check full text

DOI (Published version): 10.1007/978-3-032-00656-1_26

Abstract

Cardiac cell network segmentation is uniquely challenging because cardiomyocytes, unlike other cell types, form morphologically complex multicellular structures, causing generalist models like Cellpose to oversegment and perform inaccurately. We use our unique live cell imaging dataset of self-organ...

Full description

Published in:	Lecture Notes in Computer Science
ISBN:	9783032006554 9783032006561
ISSN:	0302-9743 1611-3349
Published:	Cham Springer Nature Switzerland 2026
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa69568

first_indexed	2025-05-26T22:02:04Z
last_indexed	2025-09-16T07:25:17Z
id	cronfa69568
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-09-15T17:09:41.3064586</datestamp><bib-version>v2</bib-version><id>69568</id><entry>2025-05-26</entry><title>Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies</title><swanseaauthors><author><sid>9d751a1fc42c90c5b7a0719cf5939280</sid><firstname>SARAH</firstname><surname>COSTA</surname><name>SARAH COSTA</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>c9972b26a83de11ffe211070f26fe16b</sid><ORCID>0000-0001-7795-453X</ORCID><firstname>Hassan</firstname><surname>Eshkiki</surname><name>Hassan Eshkiki</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>d0b8d4e63d512d4d67a02a23dd20dfdb</sid><ORCID>0000-0001-9199-7368</ORCID><firstname>Fabio</firstname><surname>Caraffini</surname><name>Fabio Caraffini</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a2e211f7bd379c81e9c393637803a0a0</sid><ORCID>0000-0001-9852-1135</ORCID><firstname>Christopher</firstname><surname>George</surname><name>Christopher George</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-05-26</date><abstract>Cardiac cell network segmentation is uniquely challenging because cardiomyocytes, unlike other cell types, form morphologically complex multicellular structures, causing generalist models like Cellpose to oversegment and perform inaccurately. We use our unique live cell imaging dataset of self-organised HL-1 networks to propose and assess various algorithmic configurations based on combinations of the Cellpose model and the Segment Anything Model, equipped with multiple pre- and post-processing routines. Our results demonstrate the advantages of integrating equalisation-based pre-processing with median filtering, fine-tuning Cellpose and incorporating our post-processing routine into the segmentation pipeline, achieving up to 85% accuracy, 96% recall, 91% DICE and 88% precision, while mitigating oversegmentation.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Lecture Notes in Computer Science</journal><volume>16039</volume><journalNumber/><paginationStart>351</paginationStart><paginationEnd>365</paginationEnd><publisher>Springer Nature Switzerland</publisher><placeOfPublication>Cham</placeOfPublication><isbnPrint>9783032006554</isbnPrint><isbnElectronic>9783032006561</isbnElectronic><issnPrint>0302-9743</issnPrint><issnElectronic>1611-3349</issnElectronic><keywords>Cell Segmentation; Cellpose; Segment Anything Model; Cardiomyocyte Networks</keywords><publishedDay>1</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-01-01</publishedDate><doi>10.1007/978-3-032-00656-1_26</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>Supported by the Morgan Advanced Studies Institute, Wales, UK; the National Cardiovascular Research Network (funded by Health and Care Research Wales); the British Heart Foundation.</funders><projectreference/><lastEdited>2025-09-15T17:09:41.3064586</lastEdited><Created>2025-05-26T22:57:55.6466250</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>SARAH</firstname><surname>COSTA</surname><order>1</order></author><author><firstname>Hassan</firstname><surname>Eshkiki</surname><orcid>0000-0001-7795-453X</orcid><order>2</order></author><author><firstname>Fabio</firstname><surname>Caraffini</surname><orcid>0000-0001-9199-7368</orcid><order>3</order></author><author><firstname>Christopher</firstname><surname>George</surname><orcid>0000-0001-9852-1135</orcid><order>4</order></author></authors><documents><document><filename>69568__34349__863332a2f91c47d8950eba45b7a28d40.pdf</filename><originalFilename>AIiH_2025.pdf</originalFilename><uploaded>2025-05-26T23:07:20.8704043</uploaded><type>Output</type><contentLength>4894922</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-09-15T17:09:41.3064586 v2 69568 2025-05-26 Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies 9d751a1fc42c90c5b7a0719cf5939280 SARAH COSTA SARAH COSTA true false c9972b26a83de11ffe211070f26fe16b 0000-0001-7795-453X Hassan Eshkiki Hassan Eshkiki true false d0b8d4e63d512d4d67a02a23dd20dfdb 0000-0001-9199-7368 Fabio Caraffini Fabio Caraffini true false a2e211f7bd379c81e9c393637803a0a0 0000-0001-9852-1135 Christopher George Christopher George true false 2025-05-26 Cardiac cell network segmentation is uniquely challenging because cardiomyocytes, unlike other cell types, form morphologically complex multicellular structures, causing generalist models like Cellpose to oversegment and perform inaccurately. We use our unique live cell imaging dataset of self-organised HL-1 networks to propose and assess various algorithmic configurations based on combinations of the Cellpose model and the Segment Anything Model, equipped with multiple pre- and post-processing routines. Our results demonstrate the advantages of integrating equalisation-based pre-processing with median filtering, fine-tuning Cellpose and incorporating our post-processing routine into the segmentation pipeline, achieving up to 85% accuracy, 96% recall, 91% DICE and 88% precision, while mitigating oversegmentation. Conference Paper/Proceeding/Abstract Lecture Notes in Computer Science 16039 351 365 Springer Nature Switzerland Cham 9783032006554 9783032006561 0302-9743 1611-3349 Cell Segmentation; Cellpose; Segment Anything Model; Cardiomyocyte Networks 1 1 2026 2026-01-01 10.1007/978-3-032-00656-1_26 COLLEGE NANME COLLEGE CODE Swansea University Not Required Supported by the Morgan Advanced Studies Institute, Wales, UK; the National Cardiovascular Research Network (funded by Health and Care Research Wales); the British Heart Foundation. 2025-09-15T17:09:41.3064586 2025-05-26T22:57:55.6466250 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science SARAH COSTA 1 Hassan Eshkiki 0000-0001-7795-453X 2 Fabio Caraffini 0000-0001-9199-7368 3 Christopher George 0000-0001-9852-1135 4 69568__34349__863332a2f91c47d8950eba45b7a28d40.pdf AIiH_2025.pdf 2025-05-26T23:07:20.8704043 Output 4894922 application/pdf Accepted Manuscript true Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
spellingShingle	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies SARAH COSTA Hassan Eshkiki Fabio Caraffini Christopher George
title_short	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
title_full	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
title_fullStr	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
title_full_unstemmed	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
title_sort	Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies
author_id_str_mv	9d751a1fc42c90c5b7a0719cf5939280 c9972b26a83de11ffe211070f26fe16b d0b8d4e63d512d4d67a02a23dd20dfdb a2e211f7bd379c81e9c393637803a0a0
author_id_fullname_str_mv	9d751a1fc42c90c5b7a0719cf5939280_*_SARAH COSTA c9972b26a83de11ffe211070f26fe16b__Hassan Eshkiki d0b8d4e63d512d4d67a02a23dd20dfdb__Fabio Caraffini a2e211f7bd379c81e9c393637803a0a0_*_Christopher George
author	SARAH COSTA Hassan Eshkiki Fabio Caraffini Christopher George
author2	SARAH COSTA Hassan Eshkiki Fabio Caraffini Christopher George
format	Conference Paper/Proceeding/Abstract
container_title	Lecture Notes in Computer Science
container_volume	16039
container_start_page	351
publishDate	2026
institution	Swansea University
isbn	9783032006554 9783032006561
issn	0302-9743 1611-3349
doi_str_mv	10.1007/978-3-032-00656-1_26
publisher	Springer Nature Switzerland
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	Cardiac cell network segmentation is uniquely challenging because cardiomyocytes, unlike other cell types, form morphologically complex multicellular structures, causing generalist models like Cellpose to oversegment and perform inaccurately. We use our unique live cell imaging dataset of self-organised HL-1 networks to propose and assess various algorithmic configurations based on combinations of the Cellpose model and the Segment Anything Model, equipped with multiple pre- and post-processing routines. Our results demonstrate the advantages of integrating equalisation-based pre-processing with median filtering, fine-tuning Cellpose and incorporating our post-processing routine into the segmentation pipeline, achieving up to 85% accuracy, 96% recall, 91% DICE and 88% precision, while mitigating oversegmentation.
published_date	2026-01-01T05:24:17Z
_version_	1851641202124783616
score	11.089988

Enhancing Cardiac Cell Networks Segmentation via Hybrid Supervised and Zero-Shot Strategies

Similar Items