Bing-Hua Chen1, Dong-Aolei An1, Jie He2, Chong-Wen Wu1, Ting Yue1, Rui Wu1, Ruo-Yang Shi1, Khalid Eteer3, Bobby Joseph3, Jiani Hu3, Jian-Rong Xu4, Lian-Ming Wu5, Jun Pu6. 1. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 160 PuJian Road, Shanghai, 200127, People's Republic of China. 2. Department of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 160 PuJian Road, Shanghai, 200127, People's Republic of China. 3. Department of Radiology, Wayne State University, Detroit, MI, 48201, USA. 4. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 160 PuJian Road, Shanghai, 200127, People's Republic of China. xujianrong0311@126.com. 5. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 160 PuJian Road, Shanghai, 200127, People's Republic of China. wlmssmu@126.com. 6. Department of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 160 PuJian Road, Shanghai, 200127, People's Republic of China. pjrenji@163.com.
Abstract
OBJECTIVES: Our study sought to explore the prognostic value of radiomic TA (texture analysis) on quantitative ECV (extracellular volume) fraction mapping to differentiate between reversible and irreversible myocardial damage and to predict left ventricular adverse remodeling in patients with reperfused STEMI (ST-elevation myocardial infarction). METHODS: This observational prospective cohort study identified 70 patients (62 ± 9 years, 62 men [85.70%]) with STEMI for TA who consecutively performed native and contrast T1 mapping. Texture features were extracted from each stack of ECV mapping based on ROI (region of interest) analysis. RESULTS: After texture feature selection and dimension reduction, five selected texture features were found to be statistically significant for differentiating the extent of myocardial injury. ROC (receiver operating characteristic) curve analysis for the differentiation of unsalvageable infarction and salvageable myocardium demonstrated a significantly higher AUC (area under the curve) (0.91 [95% CI, 0.86-0.96], p < 0.0001) for horizontal fraction than other texture features (p < 0.05). LVAR (left ventricular adverse remodeling) was predicted by those selected features. The differences in qualitative and quantitative baseline parameters and horizontal fractions were significant between the patients with and without LVAR. LGE (late gadolinium enhancement) and horizontal fraction features of infarcted myocardium in acute STEMI were the only two parameters selected in forming the optimal overall multivariable model for LVAR at 6 months. CONCLUSIONS: Radiomic analysis of ECV could discriminate reversible from irreversible myocardial injury after STEMI. LGE as well as radiomics TA (texture analysis) of ECV may provide an alternative to predict LVAR and functional recovery. KEY POINTS: • ECV quantification was able to differentiate between infarcted myocardium and non-infarcted myocardium. • Radiomics analysis of ECV could discriminate reversible from irreversible myocardial injury. • Radiomics TA analysis shows a promising similarity with LGE findings which could aid the prognosis of myocardial infarction patients.
OBJECTIVES: Our study sought to explore the prognostic value of radiomic TA (texture analysis) on quantitative ECV (extracellular volume) fraction mapping to differentiate between reversible and irreversible myocardial damage and to predict left ventricular adverse remodeling in patients with reperfused STEMI (ST-elevation myocardial infarction). METHODS: This observational prospective cohort study identified 70 patients (62 ± 9 years, 62 men [85.70%]) with STEMI for TA who consecutively performed native and contrast T1 mapping. Texture features were extracted from each stack of ECV mapping based on ROI (region of interest) analysis. RESULTS: After texture feature selection and dimension reduction, five selected texture features were found to be statistically significant for differentiating the extent of myocardial injury. ROC (receiver operating characteristic) curve analysis for the differentiation of unsalvageable infarction and salvageable myocardium demonstrated a significantly higher AUC (area under the curve) (0.91 [95% CI, 0.86-0.96], p < 0.0001) for horizontal fraction than other texture features (p < 0.05). LVAR (left ventricular adverse remodeling) was predicted by those selected features. The differences in qualitative and quantitative baseline parameters and horizontal fractions were significant between the patients with and without LVAR. LGE (late gadolinium enhancement) and horizontal fraction features of infarcted myocardium in acute STEMI were the only two parameters selected in forming the optimal overall multivariable model for LVAR at 6 months. CONCLUSIONS: Radiomic analysis of ECV could discriminate reversible from irreversible myocardial injury after STEMI. LGE as well as radiomics TA (texture analysis) of ECV may provide an alternative to predict LVAR and functional recovery. KEY POINTS: • ECV quantification was able to differentiate between infarcted myocardium and non-infarcted myocardium. • Radiomics analysis of ECV could discriminate reversible from irreversible myocardial injury. • Radiomics TA analysis shows a promising similarity with LGE findings which could aid the prognosis of myocardial infarctionpatients.
Entities:
Keywords:
Extracellular matrix; Magnetic resonance imaging; Myocardial infarction; Ventricular remodeling
Authors: Yoko Mikami; Louis Kolman; Sebastien X Joncas; John Stirrat; David Scholl; Martin Rajchl; Carmen P Lydell; Sarah G Weeks; Andrew G Howarth; James A White Journal: J Cardiovasc Magn Reson Date: 2014-10-07 Impact factor: 5.364
Authors: Jamal N Khan; Sheraz A Nazir; Mark A Horsfield; Anvesha Singh; Prathap Kanagala; John P Greenwood; Anthony H Gershlick; Gerry P McCann Journal: BMC Res Notes Date: 2015-02-25
Authors: Sophia Hammer-Hansen; W Patricia Bandettini; Li-Yueh Hsu; Steve W Leung; Sujata Shanbhag; Christine Mancini; Anders M Greve; Lars Køber; Jens Jakob Thune; Peter Kellman; Andrew E Arai Journal: Eur Heart J Cardiovasc Imaging Date: 2015-05-16 Impact factor: 6.875
Authors: Daniel R Messroghli; James C Moon; Vanessa M Ferreira; Lars Grosse-Wortmann; Taigang He; Peter Kellman; Julia Mascherbauer; Reza Nezafat; Michael Salerno; Erik B Schelbert; Andrew J Taylor; Richard Thompson; Martin Ugander; Ruud B van Heeswijk; Matthias G Friedrich Journal: J Cardiovasc Magn Reson Date: 2017-10-09 Impact factor: 5.364
Authors: Alexander Rau; Martin Soschynski; Jana Taron; Philipp Ruile; Christopher L Schlett; Fabian Bamberg; Tobias Krauss Journal: Radiologie (Heidelb) Date: 2022-08-25