Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

DOI

  • Miao Chu, Shanghai Jiao Tong University
  • ,
  • Haibo Jia, The Second Affiliated Hospital of Harbin Medical University
  • ,
  • Juan Luis Gutiérrez-Chico, Department of Cardiology, Campo de Gibraltar Health Trust, Algeciras (Cádiz), Spain.
  • ,
  • Akiko Maehara, New York Presbyterian Hospital, Columbia University, Cardiovascular Research Foundation
  • ,
  • Ziad A Ali, New York Presbyterian Hospital, Columbia University, Cardiovascular Research Foundation
  • ,
  • Xiaoling Zeng, Department of Cardiology, Fujian Medical University Union Hospital, Fuzhou, Fujian, China.
  • ,
  • Luping He, The Second Affiliated Hospital of Harbin Medical University
  • ,
  • Chen Zhao, The Second Affiliated Hospital of Harbin Medical University
  • ,
  • Mitsuaki Matsumura, Cardiovascular Research Foundation
  • ,
  • Peng Wu, Shanghai Jiao Tong University
  • ,
  • Ming Zeng, The Second Affiliated Hospital of Harbin Medical University
  • ,
  • Takashi Kubo, Wakayama Medical University
  • ,
  • Bo Xu, Chinese Academy of Medical Sciences
  • ,
  • Lianglong Chen, Department of Cardiology, Fujian Medical University Union Hospital, Fuzhou, Fujian, China.
  • ,
  • Bo Yu, The Second Affiliated Hospital of Harbin Medical University
  • ,
  • Gary S Mintz, Cardiovascular Research Foundation
  • ,
  • William Wijns, National University of Ireland Galway
  • ,
  • Niels Ramsing Holm
  • Shengxian Tu, Shanghai Jiao Tong University, Department of Cardiology, Fujian Medical University Union Hospital, Fuzhou, Fujian, China.

BACKGROUND: Intravascular optical coherence tomography (IVOCT) enables detailed plaque characterisation in-vivo, but visual assessment is time-consuming and subjective.

AIMS: This study aims to develop and validate an automatic framework for IVOCT plaque characterisation using artificial intelligence (AI).

METHODS: IVOCT pullbacks from 5 international centres were analysed in a corelab, annotating basic plaque components, inflammatory markers and other structures. A deep convolutional network with encoding-decoding architecture and pseudo-3D input was developed and trained using hybrid loss. The proposed network was integrated into commercial software to be externally validated on additional IVOCT pullbacks from three international corelabs, taking the consensus among corelabs as reference.

RESULTS: Annotated images from 509 pullbacks (391 patients) were divided into 10,517 and 1,156 cross-sections for the training and testing datasets, respectively. Dice coefficient of the model was 0.906 for fibrous plaque, 0.848 for calcium and 0.772 for lipid in the testing dataset. Excellent agreement in plaque burden quantification was observed between the model and manual measurements (R2=0.98). In the external validation, the software correctly identified 518 out of 598 plaque regions from 300 IVOCT cross-sections, with a diagnostic accuracy of 97.6%[95%CI:93.4%-99.3%] in fibrous plaque, 90.5%[95%CI:85.2%-94.1%] in lipid and 88.5%[95%CI:82.4%-92.7%] in calcium. The median time required for analysis was 21.4 (18.6-25.0) seconds per pullback.

CONCLUSIONS: A novel AI framework for automatic plaque characterisation in IVOCT was developed, providing excellent diagnostic accuracy in both internal and external validation. This model might reduce subjectivity in image interpretation and facilitate IVOCT quantification of plaque composition, with potential applications in research and IVOCT-guided PCI.

OriginalsprogEngelsk
TidsskriftEuroIntervention
Vol/bind17
Nummer1
Sider (fra-til)41-50
Antal sider10
ISSN1774-024X
DOI
StatusUdgivet - maj 2021

Se relationer på Aarhus Universitet Citationsformater

ID: 210325339