No Cover Image

Journal article 18 views 5 downloads

Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques

Benn Jessney, Xu Chen Orcid Logo, Sophie Gu, Yuan Huang Orcid Logo, Martin Goddard, Adam Brown, Daniel Obaid Orcid Logo, Michael Mahmoudi, Hector M. Garcia Garcia Orcid Logo, Stephen P. Hoole Orcid Logo, Lorenz Räber Orcid Logo, Francesco Prati Orcid Logo, Carola-Bibiane Schönlieb Orcid Logo, Michael Roberts Orcid Logo, Martin Bennett Orcid Logo

Circulation: Cardiovascular Imaging, Volume: 18, Issue: 11, Start page: e018133

Swansea University Author: Daniel Obaid Orcid Logo

  • 71376.VOR.pdf

    PDF | Version of Record

    © 2025 The Authors. Circulation: Cardiovascular Imaging is published on behalf of the American Heart Association, Inc., by Wolters Kluwer Health, Inc. This is an open access article under the terms of the Creative Commons Attribution License.

    Download (5.71MB)

Check full text

DOI (Published version): 10.1161/circimaging.125.018133

Abstract

BACKGROUND: Intracoronary optical coherence tomography (OCT) can identify changes following drug/device treatment and high-risk plaques, but analysis requires expert clinician or core laboratory interpretation, while artifacts and limited sampling markedly impair reproducibility. Assistive technolog...

Full description

Published in: Circulation: Cardiovascular Imaging
ISSN: 1941-9651 1942-0080
Published: Wolters Kluwer Health, Inc. 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71376
first_indexed 2026-02-03T10:23:10Z
last_indexed 2026-02-04T05:33:51Z
id cronfa71376
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-02-03T10:24:37.3000697</datestamp><bib-version>v2</bib-version><id>71376</id><entry>2026-02-03</entry><title>Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques</title><swanseaauthors><author><sid>1cb4b49224d4f3f2b546ed0f39e13ea8</sid><ORCID>0000-0002-3891-1403</ORCID><firstname>Daniel</firstname><surname>Obaid</surname><name>Daniel Obaid</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-02-03</date><deptcode>MEDS</deptcode><abstract>BACKGROUND: Intracoronary optical coherence tomography (OCT) can identify changes following drug/device treatment and high-risk plaques, but analysis requires expert clinician or core laboratory interpretation, while artifacts and limited sampling markedly impair reproducibility. Assistive technologies such as artificial intelligence-based analysis may therefore aid both detailed OCT interpretation and patient management. We determined if artificial intelligence-based OCT analysis (AutoOCT) can rapidly process, optimize, and analyze OCT images, and identify plaque composition changes that predict drug success/failure and high-risk plaques. METHODS: AutoOCT deep learning artificial intelligence modules were designed to correct segmentation errors from poor-quality or artifact-containing OCT images, identify tissue/plaque composition, classify plaque types, measure multiple parameters including lumen area, lipid and calcium arcs, and fibrous cap thickness, and output segmented images and clinically useful parameters. Model development used 36&#x2009;212 frames (127 whole pullbacks, 106 patients). Internal validation of tissue and plaque classification and measurements used ex vivo OCT pullbacks from autopsy arteries, while external validation for plaque stabilization and identifying high-risk plaques used core laboratory analysis of IBIS-4 (Integrated Biomarkers and Imaging Study-4) high-intensity statin (83 patients) and CLIMA (Relationship Between Coronary Plaque Morphology of Left Anterior Descending Artery and Long-Term Clinical Outcome Study; 62 patients) studies, respectively. RESULTS: AutoOCT recovered images containing common artifacts with measurements and tissue and plaque classification accuracy of 83% versus histology, equivalent to expert clinician readers. AutoOCT replicated core laboratory plaque composition changes after high-intensity statin, including reduced lesion lipid arc (13.3&#xB0; versus 12.5&#xB0;) and increased minimum fibrous cap thickness (18.9 &#xB5;m versus 24.4 &#xB5;m). AutoOCT also identified high-risk plaque features leading to patient events including minimal lumen area &lt;3.5 mm2, Lipid arc &gt;180&#xB0;, and fibrous cap thickness &lt;75 &#xB5;m, similar to the CLIMA core laboratory. CONCLUSIONS: AutoOCT-based analysis of whole coronary artery OCT identifies tissue and plaque types and measures features correlating with plaque stabilization and high-risk plaques. Artificial intelligence-based OCT analysis may augment clinician or core laboratory analysis of intracoronary OCT images for trials of drug/device efficacy and identifying high-risk lesions.</abstract><type>Journal Article</type><journal>Circulation: Cardiovascular Imaging</journal><volume>18</volume><journalNumber>11</journalNumber><paginationStart>e018133</paginationStart><paginationEnd/><publisher>Wolters Kluwer Health, Inc.</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1941-9651</issnPrint><issnElectronic>1942-0080</issnElectronic><keywords>artificial intelligence, biomarkers, deep learning, lipids, self-help devices</keywords><publishedDay>1</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-11-01</publishedDate><doi>10.1161/circimaging.125.018133</doi><url/><notes/><college>COLLEGE NANME</college><department>Medical School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MEDS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>Supported by British Heart Foundation Grants PG/18/14/33562, RG13/14/30314, RE/24/130011, TA/F/20/210001 (London), Academy of Medical Sciences Starter Grants for Clinical Lecturers (REF: SGL030\1012), Innovate UK Advancing Precision Medicine 10069871, National Institutes of Health, R01 HL150608, EPSRC Cambridge Maths in Healthcare (Nr. EP/N014588/1) and Cambridge NIHR Biomedical Research Centres.</funders><projectreference/><lastEdited>2026-02-03T10:24:37.3000697</lastEdited><Created>2026-02-03T10:15:39.7878281</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Biomedical Science</level></path><authors><author><firstname>Benn</firstname><surname>Jessney</surname><order>1</order></author><author><firstname>Xu</firstname><surname>Chen</surname><orcid>0000-0001-9925-2598</orcid><order>2</order></author><author><firstname>Sophie</firstname><surname>Gu</surname><order>3</order></author><author><firstname>Yuan</firstname><surname>Huang</surname><orcid>0000-0002-2044-099x</orcid><order>4</order></author><author><firstname>Martin</firstname><surname>Goddard</surname><order>5</order></author><author><firstname>Adam</firstname><surname>Brown</surname><order>6</order></author><author><firstname>Daniel</firstname><surname>Obaid</surname><orcid>0000-0002-3891-1403</orcid><order>7</order></author><author><firstname>Michael</firstname><surname>Mahmoudi</surname><order>8</order></author><author><firstname>Hector M. Garcia</firstname><surname>Garcia</surname><orcid>0000-0001-5100-0471</orcid><order>9</order></author><author><firstname>Stephen P.</firstname><surname>Hoole</surname><orcid>0000-0002-3530-3808</orcid><order>10</order></author><author><firstname>Lorenz</firstname><surname>R&#xE4;ber</surname><orcid>0000-0003-0824-3026</orcid><order>11</order></author><author><firstname>Francesco</firstname><surname>Prati</surname><orcid>0000-0003-0312-2030</orcid><order>12</order></author><author><firstname>Carola-Bibiane</firstname><surname>Sch&#xF6;nlieb</surname><orcid>0000-0003-0099-6306</orcid><order>13</order></author><author><firstname>Michael</firstname><surname>Roberts</surname><orcid>0000-0002-3484-5031</orcid><order>14</order></author><author><firstname>Martin</firstname><surname>Bennett</surname><orcid>0000-0002-2565-1825</orcid><order>15</order></author></authors><documents><document><filename>71376__36174__ddb6db2f7b924fc2a12dcc44fcb139e3.pdf</filename><originalFilename>71376.VOR.pdf</originalFilename><uploaded>2026-02-03T10:21:59.7904014</uploaded><type>Output</type><contentLength>5991675</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 The Authors. Circulation: Cardiovascular Imaging is published on behalf of the American Heart Association, Inc., by Wolters Kluwer Health, Inc. This is an open access article under the terms of the Creative Commons Attribution License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-02-03T10:24:37.3000697 v2 71376 2026-02-03 Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques 1cb4b49224d4f3f2b546ed0f39e13ea8 0000-0002-3891-1403 Daniel Obaid Daniel Obaid true false 2026-02-03 MEDS BACKGROUND: Intracoronary optical coherence tomography (OCT) can identify changes following drug/device treatment and high-risk plaques, but analysis requires expert clinician or core laboratory interpretation, while artifacts and limited sampling markedly impair reproducibility. Assistive technologies such as artificial intelligence-based analysis may therefore aid both detailed OCT interpretation and patient management. We determined if artificial intelligence-based OCT analysis (AutoOCT) can rapidly process, optimize, and analyze OCT images, and identify plaque composition changes that predict drug success/failure and high-risk plaques. METHODS: AutoOCT deep learning artificial intelligence modules were designed to correct segmentation errors from poor-quality or artifact-containing OCT images, identify tissue/plaque composition, classify plaque types, measure multiple parameters including lumen area, lipid and calcium arcs, and fibrous cap thickness, and output segmented images and clinically useful parameters. Model development used 36 212 frames (127 whole pullbacks, 106 patients). Internal validation of tissue and plaque classification and measurements used ex vivo OCT pullbacks from autopsy arteries, while external validation for plaque stabilization and identifying high-risk plaques used core laboratory analysis of IBIS-4 (Integrated Biomarkers and Imaging Study-4) high-intensity statin (83 patients) and CLIMA (Relationship Between Coronary Plaque Morphology of Left Anterior Descending Artery and Long-Term Clinical Outcome Study; 62 patients) studies, respectively. RESULTS: AutoOCT recovered images containing common artifacts with measurements and tissue and plaque classification accuracy of 83% versus histology, equivalent to expert clinician readers. AutoOCT replicated core laboratory plaque composition changes after high-intensity statin, including reduced lesion lipid arc (13.3° versus 12.5°) and increased minimum fibrous cap thickness (18.9 µm versus 24.4 µm). AutoOCT also identified high-risk plaque features leading to patient events including minimal lumen area <3.5 mm2, Lipid arc >180°, and fibrous cap thickness <75 µm, similar to the CLIMA core laboratory. CONCLUSIONS: AutoOCT-based analysis of whole coronary artery OCT identifies tissue and plaque types and measures features correlating with plaque stabilization and high-risk plaques. Artificial intelligence-based OCT analysis may augment clinician or core laboratory analysis of intracoronary OCT images for trials of drug/device efficacy and identifying high-risk lesions. Journal Article Circulation: Cardiovascular Imaging 18 11 e018133 Wolters Kluwer Health, Inc. 1941-9651 1942-0080 artificial intelligence, biomarkers, deep learning, lipids, self-help devices 1 11 2025 2025-11-01 10.1161/circimaging.125.018133 COLLEGE NANME Medical School COLLEGE CODE MEDS Swansea University Another institution paid the OA fee Supported by British Heart Foundation Grants PG/18/14/33562, RG13/14/30314, RE/24/130011, TA/F/20/210001 (London), Academy of Medical Sciences Starter Grants for Clinical Lecturers (REF: SGL030\1012), Innovate UK Advancing Precision Medicine 10069871, National Institutes of Health, R01 HL150608, EPSRC Cambridge Maths in Healthcare (Nr. EP/N014588/1) and Cambridge NIHR Biomedical Research Centres. 2026-02-03T10:24:37.3000697 2026-02-03T10:15:39.7878281 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Biomedical Science Benn Jessney 1 Xu Chen 0000-0001-9925-2598 2 Sophie Gu 3 Yuan Huang 0000-0002-2044-099x 4 Martin Goddard 5 Adam Brown 6 Daniel Obaid 0000-0002-3891-1403 7 Michael Mahmoudi 8 Hector M. Garcia Garcia 0000-0001-5100-0471 9 Stephen P. Hoole 0000-0002-3530-3808 10 Lorenz Räber 0000-0003-0824-3026 11 Francesco Prati 0000-0003-0312-2030 12 Carola-Bibiane Schönlieb 0000-0003-0099-6306 13 Michael Roberts 0000-0002-3484-5031 14 Martin Bennett 0000-0002-2565-1825 15 71376__36174__ddb6db2f7b924fc2a12dcc44fcb139e3.pdf 71376.VOR.pdf 2026-02-03T10:21:59.7904014 Output 5991675 application/pdf Version of Record true © 2025 The Authors. Circulation: Cardiovascular Imaging is published on behalf of the American Heart Association, Inc., by Wolters Kluwer Health, Inc. This is an open access article under the terms of the Creative Commons Attribution License. true eng https://creativecommons.org/licenses/by/4.0/
title Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
spellingShingle Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
Daniel Obaid
title_short Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
title_full Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
title_fullStr Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
title_full_unstemmed Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
title_sort Artificial Intelligence-Led Whole Coronary Artery OCT Analysis; Validation and Identification of Drug Efficacy and Higher-Risk Plaques
author_id_str_mv 1cb4b49224d4f3f2b546ed0f39e13ea8
author_id_fullname_str_mv 1cb4b49224d4f3f2b546ed0f39e13ea8_***_Daniel Obaid
author Daniel Obaid
author2 Benn Jessney
Xu Chen
Sophie Gu
Yuan Huang
Martin Goddard
Adam Brown
Daniel Obaid
Michael Mahmoudi
Hector M. Garcia Garcia
Stephen P. Hoole
Lorenz Räber
Francesco Prati
Carola-Bibiane Schönlieb
Michael Roberts
Martin Bennett
format Journal article
container_title Circulation: Cardiovascular Imaging
container_volume 18
container_issue 11
container_start_page e018133
publishDate 2025
institution Swansea University
issn 1941-9651
1942-0080
doi_str_mv 10.1161/circimaging.125.018133
publisher Wolters Kluwer Health, Inc.
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Biomedical Science{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Biomedical Science
document_store_str 1
active_str 0
description BACKGROUND: Intracoronary optical coherence tomography (OCT) can identify changes following drug/device treatment and high-risk plaques, but analysis requires expert clinician or core laboratory interpretation, while artifacts and limited sampling markedly impair reproducibility. Assistive technologies such as artificial intelligence-based analysis may therefore aid both detailed OCT interpretation and patient management. We determined if artificial intelligence-based OCT analysis (AutoOCT) can rapidly process, optimize, and analyze OCT images, and identify plaque composition changes that predict drug success/failure and high-risk plaques. METHODS: AutoOCT deep learning artificial intelligence modules were designed to correct segmentation errors from poor-quality or artifact-containing OCT images, identify tissue/plaque composition, classify plaque types, measure multiple parameters including lumen area, lipid and calcium arcs, and fibrous cap thickness, and output segmented images and clinically useful parameters. Model development used 36 212 frames (127 whole pullbacks, 106 patients). Internal validation of tissue and plaque classification and measurements used ex vivo OCT pullbacks from autopsy arteries, while external validation for plaque stabilization and identifying high-risk plaques used core laboratory analysis of IBIS-4 (Integrated Biomarkers and Imaging Study-4) high-intensity statin (83 patients) and CLIMA (Relationship Between Coronary Plaque Morphology of Left Anterior Descending Artery and Long-Term Clinical Outcome Study; 62 patients) studies, respectively. RESULTS: AutoOCT recovered images containing common artifacts with measurements and tissue and plaque classification accuracy of 83% versus histology, equivalent to expert clinician readers. AutoOCT replicated core laboratory plaque composition changes after high-intensity statin, including reduced lesion lipid arc (13.3° versus 12.5°) and increased minimum fibrous cap thickness (18.9 µm versus 24.4 µm). AutoOCT also identified high-risk plaque features leading to patient events including minimal lumen area <3.5 mm2, Lipid arc >180°, and fibrous cap thickness <75 µm, similar to the CLIMA core laboratory. CONCLUSIONS: AutoOCT-based analysis of whole coronary artery OCT identifies tissue and plaque types and measures features correlating with plaque stabilization and high-risk plaques. Artificial intelligence-based OCT analysis may augment clinician or core laboratory analysis of intracoronary OCT images for trials of drug/device efficacy and identifying high-risk lesions.
published_date 2025-11-01T05:35:19Z
_version_ 1856896520078491648
score 11.095902

Similar Items