Prediction of the development of new coronary atherosclerotic plaques with radiomics.

Coronary artery atherosclerosis Coronary artery disease Coronary computed tomography angiography Radiomics

Journal

Journal of cardiovascular computed tomography
ISSN: 1876-861X
Titre abrégé: J Cardiovasc Comput Tomogr
Pays: United States
ID NLM: 101308347

Informations de publication

Date de publication:
19 Feb 2024
Historique:
received: 20 11 2023
revised: 01 02 2024
accepted: 12 02 2024
medline: 21 2 2024
pubmed: 21 2 2024
entrez: 20 2 2024
Statut: aheadofprint

Résumé

Radiomics is expected to identify imaging features beyond the human eye. We investigated whether radiomics can identify coronary segments that will develop new atherosclerotic plaques on coronary computed tomography angiography (CCTA). From a prospective multinational registry of patients with serial CCTA studies at ≥ 2-year intervals, segments without identifiable coronary plaque at baseline were selected and radiomic features were extracted. Cox models using clinical risk factors (Model 1), radiomic features (Model 2) and both clinical risk factors and radiomic features (Model 3) were constructed to predict the development of a coronary plaque, defined as total PV ​≥ ​1 ​mm In total, 9583 normal coronary segments were identified from 1162 patients (60.3 ​± ​9.2 years, 55.7% male) and divided 8:2 into training and test sets. At follow-up CCTA, 9.8% of the segments developed new coronary plaque. The predictive power of Models 1 and 2 was not different in both the training and test sets (C-index [95% confidence interval (CI)] of Model 1 vs. Model 2: 0.701 [0.690-0.712] vs. 0.699 [0.0.688-0.710] and 0.696 [0.671-0.725] vs. 0.0.691 [0.667-0.715], respectively, all p ​> ​0.05). The addition of radiomic features to clinical risk factors improved the predictive power of the Cox model in both the training and test sets (C-index [95% CI] of Model 3: 0.772 [0.762-0.781] and 0.767 [0.751-0.787], respectively, all p ​< ​00.0001 compared to Models 1 and 2). Radiomic features can improve the identification of segments that would develop new coronary atherosclerotic plaque. ClinicalTrials.gov NCT0280341.

Sections du résumé

BACKGROUND BACKGROUND
Radiomics is expected to identify imaging features beyond the human eye. We investigated whether radiomics can identify coronary segments that will develop new atherosclerotic plaques on coronary computed tomography angiography (CCTA).
METHODS METHODS
From a prospective multinational registry of patients with serial CCTA studies at ≥ 2-year intervals, segments without identifiable coronary plaque at baseline were selected and radiomic features were extracted. Cox models using clinical risk factors (Model 1), radiomic features (Model 2) and both clinical risk factors and radiomic features (Model 3) were constructed to predict the development of a coronary plaque, defined as total PV ​≥ ​1 ​mm
RESULTS RESULTS
In total, 9583 normal coronary segments were identified from 1162 patients (60.3 ​± ​9.2 years, 55.7% male) and divided 8:2 into training and test sets. At follow-up CCTA, 9.8% of the segments developed new coronary plaque. The predictive power of Models 1 and 2 was not different in both the training and test sets (C-index [95% confidence interval (CI)] of Model 1 vs. Model 2: 0.701 [0.690-0.712] vs. 0.699 [0.0.688-0.710] and 0.696 [0.671-0.725] vs. 0.0.691 [0.667-0.715], respectively, all p ​> ​0.05). The addition of radiomic features to clinical risk factors improved the predictive power of the Cox model in both the training and test sets (C-index [95% CI] of Model 3: 0.772 [0.762-0.781] and 0.767 [0.751-0.787], respectively, all p ​< ​00.0001 compared to Models 1 and 2).
CONCLUSION CONCLUSIONS
Radiomic features can improve the identification of segments that would develop new coronary atherosclerotic plaque.
CLINICAL TRIAL REGISTRATION BACKGROUND
ClinicalTrials.gov NCT0280341.

Identifiants

pubmed: 38378314
pii: S1934-5925(24)00032-7
doi: 10.1016/j.jcct.2024.02.003
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2024 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of competing interest Dr. Chang receives funding from the Leading Foreign Research Institute Recruitment Program through the National Research Foundation (NRF) of Korea funded by the Ministry of Science and ICT (MSIT) (Grant No. 2012027176). Dr. James K. Min receives funding from GE Healthcare and serves on the scientific advisory board of Arineta and GE Healthcare. Dr. Min also has an equity interest in and is an employee of Cleerly, Inc. The remaining authors have no relevant disclosures.

Auteurs

Sang-Eun Lee (SE)

Division of Cardiology, Department of Internal Medicine, College of Medicine, Ewha Womans University, Seoul, South Korea; CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea.

Youngtaek Hong (Y)

CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea.

Jongsoo Hong (J)

Division of Biostatistics, Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, South Korea.

Juyeong Jung (J)

Graduate School of Medical Science, Brain Korea 21 Project, Yonsei University College of Medicine, Seoul, South Korea.

Ji Min Sung (JM)

CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea.

Daniele Andreini (D)

IRCCS Ospedale Galeazzi Sant'Ambrogio, Milan, Italy; Department of Biomedical and Clinical Sciences, University of Milan, Milan, Italy.

Mouaz H Al-Mallah (MH)

Houston Methodist DeBakey Heart & Vascular Center, Houston Methodist Hospital, Houston, TX, USA.

Matthew J Budoff (MJ)

Department of Medicine, Lundquist Institute at Harbor-UCLA, Torrance, CA, USA.

Filippo Cademartiri (F)

Department of Radiology, Fondazione Monasterio, Pisa, Italy.

Kavitha Chinnaiyan (K)

Department of Cardiology, William Beaumont Hospital, Royal Oak, MI, USA.

Jung Hyun Choi (JH)

Pusan University Hospital, Busan, South Korea.

Eun Ju Chun (EJ)

Seoul National University Bundang Hospital, Seongnam, South Korea.

Edoardo Conte (E)

Centro Cardiologico Monzino IRCCS, Milan, Italy.

Ilan Gottlieb (I)

Department of Radiology, Casa de Saude São Jose, Rio de Janeiro, Brazil.

Martin Hadamitzky (M)

Department of Radiology and Nuclear Medicine, German Heart Center Munich, Munich, Germany.

Yong Jin Kim (YJ)

Department of Internal Medicine, Seoul National University College of Medicine, Cardiovascular Center, Seoul National University Hospital, Seoul, South Korea.

Byoung Kwon Lee (BK)

Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.

Jonathon A Leipsic (JA)

Department of Medicine and Radiology, University of British Columbia, Vancouver, BC, Canada.

Erica Maffei (E)

Department of Radiology, Area Vasta 1/ Azienda Sanitaria Unica Regionale (ASUR) Marche, Urbino, Italy.

Hugo Marques (H)

UNICA, Unit of Cardiovascular Imaging, Hospital da Luz, Lisbon, Portugal.

Pedro de Araújo Gonçalves (PA)

UNICA, Unit of Cardiovascular Imaging, Hospital da Luz, Lisbon, Portugal.

Gianluca Pontone (G)

Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical, Dental and Surgical Sciences, University of Milan, Milan, Italy.

Sanghoon Shin (S)

Division of Cardiology, Department of Internal Medicine, College of Medicine, Ewha Womans University, Seoul, South Korea.

Peter H Stone (PH)

Division of Cardiovascular Medicine, Brigham and Women's Hospital, Boston, MA, USA.

Habib Samady (H)

Georgia Heart Institute, Northeast Georgia Health System, Gainesville, GA, USA.

Renu Virmani (R)

Department of Pathology, CVPath Institute, Gaithersburg, MD, USA.

Jagat Narula (J)

University of Texas Health Houston, Houston, TX, USA.

Leslee J Shaw (LJ)

Icahn School of Medicine at Mount Sinai, New York, NY, USA.

Jeroen J Bax (JJ)

Department of Cardiology, Leiden University Medical Center, Leiden, The Netherlands.

Fay Y Lin (FY)

Icahn School of Medicine at Mount Sinai, New York, NY, USA.

James K Min (JK)

Cleerly, Inc, New York, NY, USA.

Hyuk-Jae Chang (HJ)

CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, South Korea; Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Yonsei University Health System, Seoul, South Korea. Electronic address: hjchang@yuhs.ac.

Classifications MeSH