Open Access
Open access
European Heart Journal - Digital Health

Examination of the performance of machine learning-based automated coronary plaque characterization by NIRS-IVUS and OCT with histology

Retesh Bajaj 1, 2, 3
Ramya Parasa 1, 2, 4
Alexander Broersen 5
Thomas Johnson 6
Mohil Garg 7
Francesco Prati 8, 9
Murat Çap 1
Nathan Angelo Lecaros Yap 2
Medeni Karaduman 10
Carol Ann Glorioso Rexen Busk 11, 12, 13
Stephanie Grainger 14
Steven White 15
Anthony Mathur 1, 2
Hector M. García-García 7
Jouke Dijkstra 16
Ryo Torii 17
Andreas Baumbach 1, 2
Helle Precht 11, 12, 13
Christos V. Bourantas 1, 2
Show full list: 19 authors
1
 
Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust , London ,
2
 
Centre for Cardiovascular Medicine and Device Innovation, William Harvey Research Institute, Queen Mary University of London ,
3
 
Ottawa Heart Institute , Ontario ,
4
 
The Essex Cardiothoracic Centre , Basildon ,
7
 
Department of Cardiology, Medstar Cardiovascular Research Network, Medstar Washington Hospital Center , Washington, District of Columbia
8
 
Cardiovascular Sciences Department, Interventional Cardiology Unit, San Giovanni Addolorata Hospital , Rome ,
9
 
Centro per la Lotta Contro L’Infarto - CLI Foundation , Rome ,
10
 
Department of Cardiology, Faculty of Medicine Yuzuncu Yil University Van ,
11
 
Health Sciences Research Centre, UCL University College , Odense ,
12
 
Department of Radiology, Lillebaelt Hospital, University Hospitals of Southern Denmark ,
14
 
Infraredx , Bedford, MA ,
15
 
Biosciences Institute, Newcastle University ,
16
 
Department of Radiology, Leiden University Medical Center , Leiden ,
17
 
Department of Mechanical Engineering, University College London , London ,
Publication typeJournal Article
Publication date2025-03-04
wos Q1
SJR
CiteScore5.0
Impact factor3.9
ISSN26343916
Abstract
Aims

Near-infrared spectroscopy-intravascular ultrasound (NIRS-IVUS) and optical coherence tomography (OCT) can assess coronary plaque pathology but are limited by time-consuming and expertise-driven image analysis. Recently introduced machine learning(ML)-classifiers have expedited image processing, but their performance in assessing plaque pathology against histological standards remains unclear. The aim of this study is to assess the performance of NIRS-IVUS-ML-based and OCT-ML-based plaque characterization against a histological standard.

Methods and Results

Matched histological and NIRS-IVUS/OCT frames from human cadaveric hearts were manually annotated and fibrotic(FT), calcific(Ca) and necrotic core(NC) regions-of-interest(ROIs) were identified. NIRS-IVUS and OCT frames were processed by their respective ML-classifiers to segment and characterize plaque components. The histologically-defined ROIs were overlaid onto corresponding NIRS-IVUS/OCT frames and the ML-classifier estimations compared with histology.

In total 131 pairs of NIRS-IVUS/histology and 184 pairs of OCT/histology were included. The agreement of NIRS-IVUS-ML with histology (concordance correlation coefficient(CCC) 0.81 and 0.88) was superior to OCT-ML (CCC 0.64 and 0.73) for the plaque area and burden. Plaque compositional analysis showed a substantial agreement of the NIRS-IVUS-ML with histology for FT, Ca and NC ROIs (CCC: 0.73, 0.75 and 0.66, respectively) while the agreement of the OCT-ML with histology was 0.42, 0.62 and 0.13, respectively. The overall accuracy of NIRS-IVUS-ML and OCT-ML for characterizing atheroma types was 83% and 72%, respectively.

Conclusions

NIRS-IVUS-ML plaque compositional analysis has a good performance in assessing plaque components while OCT-ML performs well for the FT, moderately for the Ca and has weak performance in detecting NC tissue. This may be attributable to limitations of standalone intravascular imaging and to the fact that the OCT-ML classifier was trained on human experts rather than histological standards.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Share
Cite this
GOST | RIS | BibTex
Found error?