Andrew Lin1, Márton Kolossváry2, Sebastien Cadet3, Priscilla McElhinney4, Markus Goeller5, Donghee Han3, Jeremy Yuvaraj6, Nitesh Nerlekar6, Piotr J Slomka7, Mohamed Marwan5, Stephen J Nicholls6, Stephan Achenbach5, Pál Maurovich-Horvat8, Dennis T L Wong6, Damini Dey9. 1. Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA; Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University and MonashHeart, Monash Health, Melbourne, Victoria, Australia. 2. Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA. 3. Department of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, California, USA. 4. Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA. 5. Department of Cardiology, Friedrich-Alexander-University Erlangen-Nürnberg, Faculty of Medicine, Erlangen, Germany. 6. Monash Cardiovascular Research Centre, Victorian Heart Institute, Monash University and MonashHeart, Monash Health, Melbourne, Victoria, Australia. 7. Artificial Intelligence in Medicine Program, Cedars-Sinai Medical Center, Los Angeles, California, USA. 8. Medical Imaging Centre, Semmelweis University, Budapest, Hungary; MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, Budapest, Hungary. 9. Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA. Electronic address: damini.dey@cshs.org.
Abstract
OBJECTIVES: The aim of this study was to precisely phenotype culprit and nonculprit lesions in myocardial infarction (MI) and lesions in stable coronary artery disease (CAD) using coronary computed tomography angiography (CTA)-based radiomic analysis. BACKGROUND: It remains debated whether any single coronary atherosclerotic plaque within the vulnerable patient exhibits unique morphology conferring an increased risk of clinical events. METHODS: A total of 60 patients with acute MI prospectively underwent coronary CTA before invasive angiography and were matched to 60 patients with stable CAD. For all coronary lesions, high-risk plaque (HRP) characteristics were qualitatively assessed, followed by semiautomated plaque quantification and extraction of 1,103 radiomic features. Machine learning models were built to examine the additive value of radiomic features for discriminating culprit lesions over and above HRP and plaque volumes. RESULTS: Culprit lesions had higher mean volumes of noncalcified plaque (NCP) and low-density noncalcified plaque (LDNCP) compared with the highest-grade stenosis nonculprits and highest-grade stenosis stable CAD lesions (NCP: 138.1 mm3 vs 110.7 mm3 vs 102.7 mm3; LDNCP: 14.2 mm3 vs 9.8 mm3 vs 8.4 mm3; both Ptrend < 0.01). In multivariable linear regression adjusted for NCP and LDNCP volumes, 14.9% (164 of 1,103) of radiomic features were associated with culprits and 9.7% (107 of 1,103) were associated with the highest-grade stenosis nonculprits (critical P < 0.0007) when compared with highest-grade stenosis stable CAD lesions as reference. Hierarchical clustering of significant radiomic features identified 9 unique data clusters (latent phenotypes): 5 contained radiomic features specific to culprits, 1 contained features specific to highest-grade stenosis nonculprits, and 3 contained features associated with either lesion type. Radiomic features provided incremental value for discriminating culprit lesions when added to a machine learning model containing HRP and plaque volumes (area under the receiver-operating characteristic curve 0.86 vs 0.76; P = 0.004). CONCLUSIONS: Culprit lesions and highest-grade stenosis nonculprit lesions in MI have distinct radiomic signatures compared with lesions in stable CAD. Within the vulnerable patient may exist individual vulnerable plaques identifiable by coronary CTA-based precision phenotyping.
OBJECTIVES: The aim of this study was to precisely phenotype culprit and nonculprit lesions in myocardial infarction (MI) and lesions in stable coronary artery disease (CAD) using coronary computed tomography angiography (CTA)-based radiomic analysis. BACKGROUND: It remains debated whether any single coronary atherosclerotic plaque within the vulnerable patient exhibits unique morphology conferring an increased risk of clinical events. METHODS: A total of 60 patients with acute MI prospectively underwent coronary CTA before invasive angiography and were matched to 60 patients with stable CAD. For all coronary lesions, high-risk plaque (HRP) characteristics were qualitatively assessed, followed by semiautomated plaque quantification and extraction of 1,103 radiomic features. Machine learning models were built to examine the additive value of radiomic features for discriminating culprit lesions over and above HRP and plaque volumes. RESULTS: Culprit lesions had higher mean volumes of noncalcified plaque (NCP) and low-density noncalcified plaque (LDNCP) compared with the highest-grade stenosis nonculprits and highest-grade stenosis stable CAD lesions (NCP: 138.1 mm3 vs 110.7 mm3 vs 102.7 mm3; LDNCP: 14.2 mm3 vs 9.8 mm3 vs 8.4 mm3; both Ptrend < 0.01). In multivariable linear regression adjusted for NCP and LDNCP volumes, 14.9% (164 of 1,103) of radiomic features were associated with culprits and 9.7% (107 of 1,103) were associated with the highest-grade stenosis nonculprits (critical P < 0.0007) when compared with highest-grade stenosis stable CAD lesions as reference. Hierarchical clustering of significant radiomic features identified 9 unique data clusters (latent phenotypes): 5 contained radiomic features specific to culprits, 1 contained features specific to highest-grade stenosis nonculprits, and 3 contained features associated with either lesion type. Radiomic features provided incremental value for discriminating culprit lesions when added to a machine learning model containing HRP and plaque volumes (area under the receiver-operating characteristic curve 0.86 vs 0.76; P = 0.004). CONCLUSIONS: Culprit lesions and highest-grade stenosis nonculprit lesions in MI have distinct radiomic signatures compared with lesions in stable CAD. Within the vulnerable patient may exist individual vulnerable plaques identifiable by coronary CTA-based precision phenotyping.
Authors: Kristian Thygesen; Joseph S Alpert; Allan S Jaffe; Bernard R Chaitman; Jeroen J Bax; David A Morrow; Harvey D White Journal: J Am Coll Cardiol Date: 2018-08-25 Impact factor: 24.094
Authors: Gregg W Stone; Akiko Maehara; Ziad A Ali; Claes Held; Mitsuaki Matsumura; Lars Kjøller-Hansen; Hans Erik Bøtker; Michael Maeng; Thomas Engstrøm; Rune Wiseth; Jonas Persson; Thor Trovik; Ulf Jensen; Stefan K James; Gary S Mintz; Ovidiu Dressler; Aaron Crowley; Ori Ben-Yehuda; David Erlinge Journal: J Am Coll Cardiol Date: 2020-10-15 Impact factor: 24.094
Authors: Pál Maurovich-Horvat; Christopher L Schlett; Hatem Alkadhi; Masataka Nakano; Fumiyuki Otsuka; Paul Stolzmann; Hans Scheffel; Maros Ferencik; Matthias F Kriegel; Harald Seifarth; Renu Virmani; Udo Hoffmann Journal: JACC Cardiovasc Imaging Date: 2012-12
Authors: Andrew Lin; Márton Kolossváry; Jeremy Yuvaraj; Sebastien Cadet; Priscilla A McElhinney; Cathy Jiang; Nitesh Nerlekar; Stephen J Nicholls; Piotr J Slomka; Pál Maurovich-Horvat; Dennis T L Wong; Damini Dey Journal: JACC Cardiovasc Imaging Date: 2020-08-26
Authors: Márton Kolossváry; Júlia Karády; Yasuka Kikuchi; Alexander Ivanov; Christopher L Schlett; Michael T Lu; Borek Foldyna; Béla Merkely; Hugo J Aerts; Udo Hoffmann; Pál Maurovich-Horvat Journal: Radiology Date: 2019-08-06 Impact factor: 11.105