Automated segmentation and clinical characterization of layered plaque in intracoronary optical coherence tomography.

Authors

Ruben G A van der Waerden, Joske L van der Zande, Simone Saitta, Rick H J A Volleberg, Jan-Quinten Mol, Pierandrea Cancian, Thijs J Luttikholt, Xiaojin Gu, Leah Heil, Maarten van Leeuwen, Martijn Meuwissen, Alexey V Protopopov, Peep Laanmets, Oleg V Krestyaninov, Robert Dennert, Rohit M Oemrawsingh, Jan-Peter van Kuijk, Karin Arkenbout, Dirk J van der Heijden, Elvin Kedhi, Tomasz Roleder, Clara I Sánchez, Bram van Ginneken, Ivana Išgum, Jos Thannhauser, Niels van Royen

Published in

International journal of cardiology. Heart & vasculature. Volume 67. Pages 102025. Epub Oct 09, 2026.

Abstract

Layered plaque, representing organized thrombus overlying a previously disrupted plaque, is a marker of coronary destabilization and plaque vulnerability. Despite its clinical relevance, identifying layered plaque remains expert dependent with interobserver variability, limiting large-scale assessment. We developed and validated an artificial intelligence (AI) model for layered plaque segmentation, and assessed occurrence and associations with plaque vulnerability in non-culprit lesions.
Optical coherence tomography (OCT) pullbacks from the PECTUS-obs and ORANGE datasets were used to develop an enhanced version of our validated multiclass segmentation model (OCT-AID), by adding layered plaque as an additional pixel-level class. Pullbacks were divided into a training set (n = 4121 frames, 493 with layered plaque) and an independent held-out test set (n = 433 frames, 71 with layered plaque). Using this model, prevalence of layered plaque and associations with plaque vulnerability features were studied in patients with non-culprit lesions (PECTUS-obs data; 414 patients, 488 lesions).
The model achieved a Dice coefficient of 0.68 ± 0.27 for layered plaque segmentation, with pullback-level sensitivity of 96.2% and specificity of 75.0%. At least one layered plaque was present in 366/414 patients (88.4%). Presence of layered plaque was higher in STEMI patients (p = 0.018). Lesions containing layered plaques showed higher prevalence of lipid-rich plaque (76.4% vs. 60.9%, p = 0.008), thin-cap fibroatheroma (29.2% vs. 15.6%, p = 0.016), macrophage accumulation (25.0% vs 9.4%, p = 0.010), and cholesterol clefts (0.0% vs. 8.3%; p = 0.009).
Automated OCT-based identification of layered plaque using AI is feasible. In non-culprit coronary lesions, layered plaque was highly prevalent and associated with established markers of plaque vulnerability.

PMID:
42894801
Bibliographic data and abstract were imported from PubMed on 19 Oct 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.