1
|
Sawano S, Kodera S, Sato M, Katsushika S, Sukeda I, Takeuchi H, Shinohara H, Kobayashi A, Takiguchi H, Hirose K, Kamon T, Saito A, Kiriyama H, Miura M, Minatsuki S, Kikuchi H, Higashikuni Y, Takeda N, Fujiu K, Ando J, Akazawa H, Morita H, Komuro I. Age prediction from coronary angiography using a deep neural network: Age as a potential label to extract prognosis-related imaging features. PLoS One 2022; 17:e0276928. [PMID: 36301966 PMCID: PMC9612526 DOI: 10.1371/journal.pone.0276928] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2022] [Accepted: 10/16/2022] [Indexed: 12/03/2022] Open
Abstract
Coronary angiography (CAG) is still considered the reference standard for coronary artery assessment, especially in the treatment of acute coronary syndrome (ACS). Although aging causes changes in coronary arteries, the age-related imaging features on CAG and their prognostic relevance have not been fully characterized. We hypothesized that a deep neural network (DNN) model could be trained to estimate vascular age only using CAG and that this age prediction from CAG could show significant associations with clinical outcomes of ACS. A DNN was trained to estimate vascular age using ten separate frames from each of 5,923 CAG videos from 572 patients. It was then tested on 1,437 CAG videos from 144 patients. Subsequently, 298 ACS patients who underwent percutaneous coronary intervention (PCI) were analysed to assess whether predicted age by DNN was associated with clinical outcomes. Age predicted as a continuous variable showed mean absolute error of 4 years with R squared of 0.72 (r = 0.856). Among the ACS patients stratified by predicted age from CAG images before PCI, major adverse cardiovascular events (MACE) were more frequently observed in the older vascular age group than in the younger vascular age group (p = 0.017). Furthermore, after controlling for actual age, gender, peak creatine kinase, and history of heart failure, the older vascular age group independently suffered from more MACE (hazard ratio 2.14, 95% CI 1.07 to 4.29, p = 0.032). The vascular age estimated based on CAG imaging by DNN showed high predictive value. The age predicted from CAG images by DNN could have significant associations with clinical outcomes in patients with ACS.
Collapse
Affiliation(s)
- Shinnosuke Sawano
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Satoshi Kodera
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
- * E-mail:
| | - Masataka Sato
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Susumu Katsushika
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Issei Sukeda
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hirotoshi Takeuchi
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hiroki Shinohara
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Atsushi Kobayashi
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hiroshi Takiguchi
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Kazutoshi Hirose
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Tatsuya Kamon
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Akihito Saito
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hiroyuki Kiriyama
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Mizuki Miura
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Shun Minatsuki
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hironobu Kikuchi
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Yasutomi Higashikuni
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Norifumi Takeda
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Katsuhito Fujiu
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
- Department of Advanced Cardiology, The University of Tokyo, Tokyo, Japan
| | - Jiro Ando
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hiroshi Akazawa
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Hiroyuki Morita
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| | - Issei Komuro
- Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan
| |
Collapse
|
2
|
Nappi C, Gaudieri V, Acampa W, Arumugam P, Assante R, Zampella E, Mannarino T, Mainolfi CG, Imbriaco M, Petretta M, Cuocolo A. Coronary vascular age: An alternate means for predicting stress-induced myocardial ischemia in patients with suspected coronary artery disease. J Nucl Cardiol 2019; 26:1348-1355. [PMID: 29359274 DOI: 10.1007/s12350-018-1191-1] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2017] [Accepted: 01/04/2018] [Indexed: 12/22/2022]
Abstract
BACKGROUND Coronary artery calcium (CAC) can be used to estimate vascular age in adults, providing a convenient transformation of CAC from Agatston units into a year's scale. We investigated the role of coronary vascular age in predicting stress-induced myocardial ischemia in subjects with suspected coronary artery disease (CAD). METHODS A total of 717 subjects referred to CAC scoring and 82Rb PET/CT stress-rest myocardial perfusion imaging for suspected CAD were studied. CAC score was measured according to the Agatston method and coronary vascular age by equating estimated CAD risk for chronological age and CAC using the formula 39.1 + 7.25 × ln(CAC + 1). RESULTS Stress-induced ischemia was present in 105 (15%) patients. Mean chronological age, CAC score, and coronary vascular age were higher (all P < .001) in patients with ischemia compared to those without. At incremental analysis, the global Chi square increased from 41.26 to 68.77 (P < .001) when chronological age was added to clinical variables. Including vascular age in the model, the global Chi square further increased from 68.77 to 106.38 (P < .001). Adding chronological age to clinical data, continuous net reclassification improvement (cNRI) was 0.57, while adding vascular age to clinical data and chronological age cNRI was 0.62. At decision curve analysis, the model including vascular age was associated with the highest net benefit compared to the model including only clinical data, to the model including chronological age and clinical data, and to a strategy considering that all patients had ischemia. The model including vascular age also showed the largest reduction in false-positive rate without missing any ischemic patients. CONCLUSIONS In subjects with suspected CAD, coronary vascular age is strongly associated with stress-induced ischemia. The communication of a given vascular age would have a superior emotive impact improving observance of therapies and healthier lifestyles.
Collapse
Affiliation(s)
- Carmela Nappi
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Valeria Gaudieri
- Institute of Biostructure and Bioimaging, National Council of Research, Naples, Italy
| | - Wanda Acampa
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
- Institute of Biostructure and Bioimaging, National Council of Research, Naples, Italy
| | - Parthiban Arumugam
- Department of Nuclear Medicine, Central Manchester University Hospitals, Manchester, UK
| | - Roberta Assante
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Emilia Zampella
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Teresa Mannarino
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Ciro Gabriele Mainolfi
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Massimo Imbriaco
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy
| | - Mario Petretta
- Department of Translational Medical Sciences, University Federico II, Naples, Italy
| | - Alberto Cuocolo
- Department of Advanced Biomedical Sciences, University Federico II, Via Pansini 5, 80131, Naples, Italy.
| |
Collapse
|
4
|
Nappi C, Gaudieri V, Cuocolo A. Behind Traditional Semi-quantitative Scores of Myocardial Perfusion Imaging: An Eye on Niche Parameters. Eur Cardiol 2019; 14:13-17. [PMID: 31131032 PMCID: PMC6523048 DOI: 10.15420/ecr.2019.5.1] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
The evaluation of stress-induced myocardial perfusion defects by non-invasive myocardial perfusion imaging (MPI) modalities has a leading role in the identification of coronary artery disease, and has excellent diagnostic and prognostic value. Non-invasive MPI can be performed using conventional and novel gamma cameras or by PET/CT. New software has allowed novel parameters that may have a role in the identification of early marks of cardiac impairment to be evaluated. We aim to give an overview of niche parameters obtainable by single photon emission CT (SPECT) and PET/CT MPI that may help practitioners to detect initial signs of cardiac damage and identify new therapy targets. In particular, we summarise the role of left ventricular geometry indices for remodelling, phase analysis parameters to evaluate mechanical dyssynchrony, the concept of relative flow reserve in the evaluation of flow-limiting epicardial stenosis, vascular age and epicardial adipose tissue as early markers of atherosclerotic burden, and emerging parameters for the evaluation of myocardial innervation, such as the total defect score.
Collapse
Affiliation(s)
- Carmela Nappi
- Department of Advanced Biomedical Sciences, University Federico II Naples, Italy
| | - Valeria Gaudieri
- Department of Advanced Biomedical Sciences, University Federico II Naples, Italy
| | - Alberto Cuocolo
- Department of Advanced Biomedical Sciences, University Federico II Naples, Italy
| |
Collapse
|