Atherosclerosis risk classification with computed tomography angiography: A radiologic-pathologic validation study
- PMID: 36481054
- DOI: 10.1016/j.atherosclerosis.2022.11.013
Atherosclerosis risk classification with computed tomography angiography: A radiologic-pathologic validation study
Abstract
Background and aims: The application of machine learning to assess plaque risk phenotypes on cardiovascular CT angiography (CTA) is an area of active investigation. Studies using accepted histologic definitions of plaque risk as ground truth for machine learning models are uncommon. The aim was to evaluate the accuracy of a machine-learning software for determining plaque risk phenotype as compared to expert pathologists (histologic ground truth).
Methods: Sections of atherosclerotic plaques paired with CTA were prospectively collected from patients undergoing carotid endarterectomy at two centers. Specimens were annotated for lipid-rich necrotic core, calcification, matrix, and intraplaque hemorrhage at 2 mm spacing and classified as minimal disease, stable plaque, or unstable plaque according to a modified American Heart Association histological definition. Phenotype is determined in two steps: plaque morphology is delineated according to histological tissue definitions, followed by a machine learning classifier. The performance in derivation and validation cohorts for plaque risk categorization and stenosis was compared to histologic ground truth at each matched cross-section.
Results: A total of 496 and 408 vessel cross-sections in the derivation and validation cohorts (from 30 and 23 patients, respectively). The software demonstrated excellent agreement in the validation cohort with histological ground truth plaque risk phenotypes with weighted kappa of 0.82 [0.78-0.86] and area under the receiver operating curve for correct identification of plaque type was 0.97 [0.96, 0.98], 0.95 [0.94, 0.97], 0.99 [0.99, 1.0] for unstable plaque, stable plaque, and minimal disease, respectively. Diameter stenosis correlated poorly to histologically defined plaque type; weighted kappa 0.25 in the validation cohort.
Conclusions: A machine-learning software trained on histological ground-truth tissue inputs demonstrated high accuracy for identifying plaque stability phenotypes as compared to expert pathologists.
Keywords: Histopathology; Phenotype; Plaque stability.
Copyright © 2022 The Author(s). Published by Elsevier B.V. All rights reserved.
Conflict of interest statement
Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests:AJB and TCV are employees and shareholders of Elucid Bioimaging Inc. AR, AN, SS, and MP are employees of Elucid. AMG is an unpaid advisor to Elucid. AS and RV are employees of CVPath Institute.
Comment in
-
Artificial intelligence for high-risk plaque detection on carotid CT angiography.Atherosclerosis. 2023 Feb;366:40-41. doi: 10.1016/j.atherosclerosis.2023.01.006. Epub 2023 Jan 14. Atherosclerosis. 2023. PMID: 36682983 No abstract available.
Similar articles
-
Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography.Circ Cardiovasc Imaging. 2024 Jun;17(6):e016274. doi: 10.1161/CIRCIMAGING.123.016274. Epub 2024 Jun 18. Circ Cardiovasc Imaging. 2024. PMID: 38889214 Free PMC article.
-
Carotid Artery Plaque Calcifications: Lessons From Histopathology to Diagnostic Imaging.Stroke. 2022 Jan;53(1):290-297. doi: 10.1161/STROKEAHA.121.035692. Epub 2021 Nov 10. Stroke. 2022. PMID: 34753301 Review.
-
Correlation between computed tomography angiography and histology of carotid artery atherosclerosis: Can semi-automated imaging software predict a plaque's composition?Interv Neuroradiol. 2022 Jun;28(3):332-337. doi: 10.1177/15910199211031093. Epub 2021 Aug 16. Interv Neuroradiol. 2022. PMID: 34397307 Free PMC article.
-
Prediction of Carotid Intraplaque Hemorrhage Using Adventitial Calcification and Plaque Thickness on CTA.AJNR Am J Neuroradiol. 2016 Aug;37(8):1496-503. doi: 10.3174/ajnr.A4765. Epub 2016 Apr 21. AJNR Am J Neuroradiol. 2016. PMID: 27102316 Free PMC article.
-
Contemporary carotid imaging: from degree of stenosis to plaque vulnerability.J Neurosurg. 2016 Jan;124(1):27-42. doi: 10.3171/2015.1.JNS142452. Epub 2015 Jul 31. J Neurosurg. 2016. PMID: 26230478 Review.
Cited by
-
Development of physiologically-informed computational coronary artery plaques for use in virtual imaging trials.Med Phys. 2024 Mar;51(3):1583-1596. doi: 10.1002/mp.16959. Epub 2024 Feb 2. Med Phys. 2024. PMID: 38306457
-
Atherosclerotic plaque features relevant to rupture-risk detected by clinical photon-counting CT ex vivo: a proof-of-concept study.Eur Radiol Exp. 2024 Jan 30;8(1):14. doi: 10.1186/s41747-023-00410-4. Eur Radiol Exp. 2024. PMID: 38286959 Free PMC article.
-
Quantitative imaging biomarkers of coronary plaque morphology: insights from EVAPORATE.Front Cardiovasc Med. 2023 Aug 3;10:1204071. doi: 10.3389/fcvm.2023.1204071. eCollection 2023. Front Cardiovasc Med. 2023. PMID: 37600044 Free PMC article.
-
Editorial: Old habits die hard: from risk calculators and stenosis evaluation to phenotyping coronary atherosclerosis using cardiac CT.Front Cardiovasc Med. 2023 Jun 22;10:1235144. doi: 10.3389/fcvm.2023.1235144. eCollection 2023. Front Cardiovasc Med. 2023. PMID: 37424898 Free PMC article. No abstract available.
-
Acute Coronary Syndrome: Disparities of Pathophysiology and Mortality with and without Peripheral Artery Disease.J Pers Med. 2023 Jun 2;13(6):944. doi: 10.3390/jpm13060944. J Pers Med. 2023. PMID: 37373933 Free PMC article. Review.
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Medical