The use of artificial intelligence for predicting postinfarction myocardial viability in echocardiographic images
Abstract
Background: Evaluation of standard echocardiographic examination with artificial intelligence may help in the diagnosis of myocardial viability and function recovery after acute coronary syndrome.
Methods: Sixty-one consecutive patients with acute coronary syndrome were enrolled in the present study (43 men, mean age 61 ± 9 years). All patients underwent percutaneous coronary intervention (PCI). 533 segments of the heart echo images were used. After 12 ± 1 months of follow-up, patients had an echocardiographic evaluation. After PCI each patient underwent cardiac magnetic resonance (CMR) with late enhancement and low-dose dobutamine echocardiographic examination. For texture analysis, custom software was used (MaZda 5.20, Institute of Electronics).Linear and non-linear (neural network) discriminative analyses were performed to identify the optimal analytic method correlating with CMR regarding the necrosis extent and viability prediction after follow-up. Texture parameters were analyzed using machine learning techniques: Artificial Neural Networks, Namely Multilayer Perceptron, Nonlinear Discriminant Analysis, Support Vector Machine, and Adaboost algorithm.
Results: The mean concordance between the CMR definition of viability and three classification models in Artificial Neural Networks varied from 42% to 76%. Echo-based detection of non-viable tissue was more sensitive in the segments with the highest relative transmural scar thickness: 51–75% and 76–99%. The best results have been obtained for images with contrast for red and grey components (74% of proper classification). In dobutamine echocardiography, the results of appropriate prediction were 67% for monochromatic images.
Conclusions: Detection and semi-quantification of scar transmurality are feasible in echocardiographic images analyzed with artificial intelligence. Selected analytic methods yielded similar accuracy, and contrast enhancement contributed to the prediction accuracy of myocardial viability after myocardial infarction in 12 months of follow-up.
Keywords: neural networkartificial intelligencemyocardial infarctionmyocardial viabilitymyocardial texture
References
- Neumann FJ, Sousa-Uva M, Ahlsson A, et al. ESC Scientific Document Group. 2018 ESC/EACTS Guidelines on myocardial revascularization. Eur Heart J. 2019; 40(2): 87–165.
- Bierig SM, Mikolajczak P, Herrmann SC, et al. Comparison of myocardial contrast echocardiography derived myocardial perfusion reserve with invasive determination of coronary flow reserve. Eur J Echocardiogr. 2009; 10(2): 250–255.
- Bizopoulos P, Koutsouris D. Deep learning in cardiology. IEEE Rev Biomed Eng. 2019; 12: 168–193.
- Patel JL, Goyal RK. Applications of artificial neural networks in medical science. Curr Clin Pharmacol. 2007; 2(3): 217–226.
- Chrzanowski L, Drozdz J, Strzelecki M, et al. Application of neural networks for the analysis of intravascular ultrasound and histological aortic wall appearance-an in vitro tissue characterization study. Ultrasound Med Biol. 2008; 34(1): 103–113.
- Obuchowicz R, Kruszyńska J, Strzelecki M. Classifying median nerves in carpal tunnel syndrome: Ultrasound image analysis. Biocyber Biomed Eng. 2021; 41(2): 335–351.
- Dey D, Slomka PJ, Leeson P, et al. Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. J Am Coll Cardiol. 2019; 73(11): 1317–1335.
- Schuuring MJ, Išgum I, Cosyns B, et al. Routine echocardiography and artificial intelligence solutions. Front Cardiovasc Med. 2021; 8: 648877.
- van Smeden M, Heinze G, Van Calster B, et al. Critical appraisal of artificial intelligence-based prediction models for cardiovascular disease. Eur Heart J. 2022; 43(31): 2921–2930.
- Slart RH, Williams MC, Juarez-Orozco LE, et al. Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT. Eur J Nucl Med Mol Imaging. 2021; 48(5): 1399–1413.
- Thygesen K, Alpert JS, Jaffe AS, et al. Executive Group on behalf of the Joint European Society of Cardiology (ESC)/American College of Cardiology (ACC)/American Heart Association (AHA)/World Heart Federation (WHF) Task Force for the Universal Definition of Myocardial Infarction. Fourth Universal Definition of Myocardial Infarction (2018). J Am Coll Cardiol. 2018; 72(18): 2231–2264.
- Lang RM, Badano LP, Mor-Avi V, et al. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr. 2015; 28(1): 1–39.e14.
- Cerqueira MD, Weissman NJ, Dilsizian V, et al. American Heart Association Writing Group on Myocardial Segmentation and Registration for Cardiac Imaging. Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. J Nucl Cardiol. 2002; 9(2): 240–245.
- Strzelecki M, Szczypinski P, Materka A, et al. A software tool for automatic classification and segmentation of 2D/3D medical images. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. 2013; 702: 137–140.
- Szczypiński P, Strzelecki M, Materka A, et al. MaZda: the software package for textural analysis of biomedical images. Advances in Soft Computing. 2009: 73–84.
- Du-Yih T, Watanabe S, Tomita M. Computerized analysis for classification of heart diseases in echocardiographic images. Proceedings of 3rd IEEE International Conference on Image Processing. 1996: 283–286.
- Kahl L, Orglmeister R, Schmailzl K. A neural network based classifier for ultrasonic raw data of the myocardium. IEEE Ultrasonics Symposium Proceedings. An International Symposium (Cat. No.97CH36118). 1997: 1173–1176.
- Schapire RE. The Boosting Approach to Machine Learning: An Overview. In: Denison DD, Hansen MH, Holmes CC, Mallick B, Yu B (eds) Nonlinear Estimation and Classification. Lecture Notes in Statistics, Vol. 171. Springer 2003: 149–171.
- Eibe F, Hall MA, Witten IH. The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016.
- Freeman J, Skapura D. Neural Networks – Algorithms, Applications and Programming Techniques. Addison-Wesley 1991: 8–396.
- Kahl L, Orglmeister R, Schmailzl K. A neural network based classifier for ultrasonic raw data of the myocardium. IEEE Ultrasonics Symposium Proceedings. An International Symposium (Cat. No.97CH36118). 1997: 1173–1176.
- Mao J, Jain AK. Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans Neural Netw. 1995; 6(2): 296–317.
- Almeida AG, Carpenter JP, Cameli M, et al. Multimodality imaging of myocardial viability: an expert consensus document from the European Association of Cardiovascular Imaging (EACVI). Eur Heart J Cardiovasc Imaging. 2021; 22(8): e97–e9e125.
- Asch FM, Poilvert N, Abraham T, et al. Automated echocardiographic quantification of left ventricular ejection fraction without volume measurements using a machine learning algorithm mimicking a human expert. Circ Cardiovasc Imaging. 2019; 12(9): e009303.
- Massa D, Cataldo G, Ciliberto GR, et al. Resting echocardiographic assessment of regional wall motion, thickness and reflectivity in chronic ischemic cardiomyopathy: an alternative to the viability test? Ital Heart J. 2002; 3(1): 41–47.
- Milunski MR, Mohr GA, Wear KA, et al. Early identification with ultrasonic integrated backscatter of viable but stunned myocardium in dogs. J Am Coll Cardiol. 1989; 14(2): 462–471.
- Ohmori K, Cotter B, Leistad E, et al. Assessment of myocardial postreperfusion viability by intravenous myocardial contrast echocardiography: analysis of the intensity and texture of opacification. Circulation. 2001; 103(15): 2021–2027.
- Samad MD, Ulloa A, Wehner GJ, et al. Predicting survival from large echocardiography and electronic health record datasets: optimization with machine learning. JACC Cardiovasc Imaging. 2019; 12(4): 681–689.
- Bae RY, Belohlavek M, Greenleaf JF, et al. Myocardial contrast echocardiography: texture analysis for identification of nonperfused versus perfused myocardium. Echocardiography. 2001; 18(8): 665–672.
- Schinkel AFL, Bax JJ, Poldermans D, et al. Hibernating myocardium: diagnosis and patient outcomes. Curr Probl Cardiol. 2007; 32(7): 375–410.
- Lipiec P, Szymczyk E, Michalski B, et al. Echocardiographic quantitative analysis of resting myocardial function for the assessment of viability after myocardial infarction--comparison with magnetic resonance imaging. Kardiol Pol. 2011; 69(9): 915–922.
- Omar H, Domingos J, Patra A, et al. Quantification of cardiac bull's-eye map based on principal strain analysis for myocardial wall motion assessment in stress echocardiography. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). 2018.
- Rahmani R, Niazi P, Naseri M, et al. Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data. Rev Esp Med Nucl Imagen Mol (Engl Ed). 2019; 38(5): 275–279.
- Ruijsink B, Puyol-Antón E, Oksuz I, et al. Fully automated, quality-controlled cardiac analysis from CMR: validation and large-scale application to characterize cardiac function. JACC Cardiovasc Imaging. 2020; 13(3): 684–695.
- Fahmy AS, Rausch J, Neisius U, et al. Automated cardiac MR scar quantification in hypertrophic cardiomyopathy using deep convolutional neural networks. JACC Cardiovasc Imaging. 2018; 11(12): 1917–1918.
- Tsang W, Salgo IS, Medvedofsky D, et al. Transthoracic 3D echocardiographic left heart chamber quantification using an automated adaptive analytics algorithm. JACC Cardiovasc Imaging. 2016; 9(7): 769–782.
