Application of artificial intelligence for cardiac imaging studies: a brief literature review

Cardiovascular diseases remain the leading cause of disability and mortality. The WHO considers them the main cause of death worldwide. In recent years, artificial intelligence and neural networks have been rapidly developing and are successfully applied in cardiology. Deep learning has become a key tool in the diagnosis of cardiovascular diseases, allowing the identification of complex patterns and relationships in data, automating the segmentation of regions of interest. Deep learning methods contribute to accurate diagnosis using echocardiography, magnetic resonance imaging (MRI), and computed tomography (CT), which can alter the natural course of the disease and reduce healthcare costs. The aim of this work is to review the application of artificial intelligence, particularly deep learning, in cardiac imaging studies (CT, cardiac MRI, echocardiography).

Material and methods. The material for the review consisted of 35 articles published between 2013 and 2024. The search was carried out using the search query “deep learning AND (cardiac imaging OR CT OR cardiac MRI OR echocardiography)” in the international databases Scopus, PubMed, and Web of Science.

Results. One of the main limiting factors for the application of imaging studies with subsequent neural network analysis is segmentation, which requires a clear definition of the tissue region of interest. The manual approach to segmentation has drawbacks, such as labor intensity and significant variability between researchers. To overcome these limitations, deep learning models have been developed to automate the segmentation process. It involves training various neural network architectures on image datasets, which allows for automatic segmentation with high accuracy and analysis of myocardial status. Cardiac MRI provides valuable information about the state of the myocardium, including anatomy, heart chamber volumes, the presence of fibrosis and inflammation. Automatic segmentation of individual tissues, such as fibrous tissue, allows for a more accurate assessment of the extent and severity of fibrosis, which is necessary for risk stratification and treatment planning.

Conclusions. The application of deep learning in the analysis of cardiac imaging studies has enormous potential for improving the early diagnosis and management of cardiovascular diseases. Deep learning-based neural network models can be used as a screening method for the automated diagnosis of cardiovascular diseases.

1. Myers L., Mendis S. Cardiovascular disease research output in WHO priority areas between 2002 and 2011. J. Epidemiol. Glob. Health. 2013;4(1):23– 28. doi: 10.1016/j.jegh.2013.09.007

2. Wong N.D. Epidemiological studies of CHD and the evolution of preventive cardiology. Nat. Rev. Cardiol. 2014;11(5):276–289. doi: 10.1038/nrcardio.2014.26

3. Alqezweeni M.M., Gorbachenko V.I., Zenin O.K., Gribkov D.N., Potapov V.V., Miltykh I. Early diagnoses of chronic heart failure using neural network classifier of tensiometric blood test results. In: 2022 International Conference on Data Science and Intelligent Computing (ICDSIC). IEEE, 2022. P. 181–185. doi: 10.1109/ICDSIC56987.2022.10076007

4. Alqezweeni M.M., Gribkov D.N., Gorbachenko V.I., Potapov V.V., Miltykh I., Zenin O. Machine learning approach to the classification of tensiometric blood test results for chronic heart failure diagnosis. In: Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. P. 299–305. doi: 10.3233/FAIA240165

5. Athanasiou L., Nezami F.R., Edelman E.R. Computational Cardiology. IEEE J. Biomed. Health Inform. 2019;23(1):4–11. doi: 10.1109/JBHI.2018.2877044

6. Tsigkas G., Apostolos A., Aznaouridis K., Despotopoulos S., Chrysohoou C., Naka K.K., Davlouros P. Real-world implementation of guidelines for heart failure management: A systematic review and meta-analysis. Hellenic J. Cardiol. 2022;66:72–79. doi: 10.1016/j.hjc.2022.04.006

7. Chen Y., Zhang N., Gao Y., Zhou Z., Gao X., Liu J., Gao Z., Zhang H., Wen Z., Xu L. A coronary CT angiography-derived myocardial radiomics model for predicting adverse outcomes in chronic myocardial infarction. Int. J. Cardiol. 2024;411:132265. doi: 10.1016/j.ijcard.2024.132265

8. Guo Y., Bi L., Zhu Z., Feng D.D., Zhang R., Wang Q., Kim J. Automatic left ventricular cavity segmentation via deep spatial sequential network in 4D computed tomography. Comput. Med. Imaging. Graph. 2021;91:101952. doi: 10.1016/j.compmedimag.2021.101952

9. Peng P., Lekadir K., Gooya A., Shao L., Petersen S.E., Frangi A.F. A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. Magn. Reson. Mater. Phys. Biol. Med. 2016;29(2):155–195. doi: 10.1007/s10334-015-0521-4

10. Yepes-Calderon F., McComb J.G. Eliminating the need for manual segmentation to determine size andvolume from MRI. A proof of concept on segmenting the lateral ventricles. PLoS One. 2023;18(5):e0285414. doi: 10.1371/journal.pone.0285414

11. Li M., Zeng D., Xie Q., Xu R., Wang Y., Ma D., Shi Y., Xu X., Huang M., Fei H. A deep learning approach with temporal consistency for automatic myocardial segmentation of quantitative myocardial contrast echocardiography. Int. J. Cardiovasc. Imaging. 2021;37(6):1967–1978. doi: 10.1007/s10554-021-02181-8

12. Jun Guo B., He X., Lei Y., Harms J., Wang T., Curran W.J., Liu T., Jiang Zhang L., Yang X. Automated left ventricular myocardium segmentation using 3D deeply supervised attention U-net for coronary computed tomography angiography; CT myocardium segmentation. Med. Phys. 2020;47(4):1775–1785. doi: 10.1002/mp.14066

13. Chen C., Qin C., Qiu H., Tarroni G., Duan J., Bai W., Rueckert D. Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 2020;7:25. doi: 10.3389/fcvm.2020.00025

14. Antonopoulos A., Tsampras T., Kalykakis G., Karamanidou T., Stavropoulos T.G., Stavropoulos C. Automatic segmentation of the left ventricular myocardium in cardiac CT Scans using AI. In: 2024 IEEE International Symposium on Biomedical Imaging (ISBI). Athens, 2024. Р. 1–4. doi: 10.1109/ISBI56570.2024.10635185

15. Shoaib M.A., Lai K.W., Chuah J.H., Hum Y.C., Ali R., Dhanalakshmi S., Wang H., Wu X. Comparative studies of deep learning segmentation models for left ventricle segmentation. Front. Public Health. 2022;10:981019. doi: 10.3389/fpubh.2022.981019

16. Karamitsos T.D., Arvanitaki A., Karvounis H., Neubauer S., Ferreira V.M. Myocardial tissue characterization and fibrosis by imaging. JACC Cardiovasc. Imaging. 2020;13(5):1221–1234. doi: 10.1016/j.jcmg.2019.06.030

17. Lewis A.J.M., Burrage M.K., Ferreira V.M. Cardiovascular magnetic resonance imaging for inflammatory heart diseases. Cardiovasc. Diagn. Ther. 2020;10(3):598–609. doi: 10.21037/cdt.2019.12.09

18. Sun X., Cheng L.H., Plein S., Garg P., van der Geest R.J. Deep learning based automated left ventricle segmentation and flow quantification in 4D flow cardiac MRI. J. Cardiovasc. Magn. Reson. 2024;26(1):100003. doi: 10.1016/j.jocmr.2023.100003

19. Budai A., Suhai F.I., Csorba K., Toth A., Szabo L., Vago H., Merkely B. Fully automatic segmentation of right and left ventricle on short-axis cardiac MRI images. Comput. Med. Imaging. Graph. 2020;85:101786. doi: 10.1016/j.compmedimag.2020.101786

20. Shaaf Z.F., Jamil M.M.A., Ambar R., Alattab A.A., Yahya A.A., Asiri Y. Automatic left ventricle segmentation from short-axis cardiac MRI images based on fully convolutional neural network. Diagnostics (Basel). 2022;12(2):414. doi: 10.3390/diagnostics12020414

21. Chartsias A., Papanastasiou G., Wang C., Semple S., Newby D.E., Dharmakumar R., Tsaftaris S.A. Disentangle, align and fuse for multimodal and semi-supervised image segmentation. IEEE Trans. Med. Imaging. 2021;40(3):781–792. doi: 10.1109/TMI.2020.3036584

22. Chartsias A., Papanastasiou G., Wang C., Stirrat C., Semple S., Newby D., Dharmakumar R., Tsaftaris S.A. Multimodal cardiac segmentation using disentangled representation learning. In: Statistical Atlases and Computational Models of the Heart. MultiSequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges. Springer International Publishing, 2020. P. 128–137. doi: 10.1007/978-3-030-39074-7_14

23. Nakamori S., Amyar A., Fahmy A.S., Ngo L.H., Ishida M., Nakamura S., Omori T, Moriwaki K., Fujimoto N., Imanaka-Yoshida K., … Nezafat R. Cardiovascular magnetic resonance radiomics to identify components of the extracellular matrix in dilated cardiomyopathy. Circulation. 2024;150(1):7–18. doi: 10.1161/CIRCULATIONAHA.123.067107

24. Qin L., Chen C., Gu S., Zhou M., Xu Z., Ge Y., Yan F., Yang W. A radiomic approach to predict myocardial fibrosis on coronary CT angiography in hypertrophic cardiomyopathy. Int. J. Cardiol. 2021;337:113– 118. doi: 10.1016/j.ijcard.2021.04.060

25. Wu Z.H., Sun L.P., Liu Y.L., Dong D.D., Tong L., Deng D.D., He Y., Wang H., Sun Y.B., Dong J.Z., Xia L. Fully automatic scar segmentation for late gadolinium enhancement MRI images in left ventricle with myocardial infarction. Curr. Med. Sci. 2021;41(2):398–404. doi: 10.1007/s11596-021-2360-z

26. Zabihollahy F., Rajan S., Ukwatta E. Machine learning-based segmentation of left ventricular myocardial fibrosis from magnetic resonance imaging. Curr. Cardiol. Rep. 2020;22(8):65. doi: 10.1007/s11886-020-01321-1

27. Nauffal V., Di Achille P., Klarqvist M.D.R., Cunningham J.W., Hill M.C., Pirruccello J.P., Weng L.C., Morrill V.N., Choi S.H., Khurshid S., … Lubitz S.A. Genetics of myocardial interstitial fibrosis in the human heart and association with disease. Nat. Genet. 2023;55(5):777–786. doi: 10.1038/s41588-023-01371-5

28. Treiber J., Hausmann C.S., Wolter J.S., Fischer-Rasokat U., Kriechbaum S.D., Hamm C.W., Nagel E., Puntmann V.O., Rolf A. Native T1 is predictive of cardiovascular death/heart failure events and all-cause mortality irrespective of the patient’s volume status. Front. Cardiovasc. Med. 2023;10:1091334. doi: 10.3389/fcvm.2023.1091334

29. Raisi-Estabragh Z., McCracken C., Hann E., Condurache D.G., Harvey N.C., Munroe P.B., Ferreira V.M., Neubauer S., Piechnik S.K., Petersen S.E. Incident clinical and mortality associations of myocardial native T1 in the UK Biobank. JACC Cardiovasc. Imaging. 2023;16(4):450–460. doi: 10.1016/j.jcmg.2022.06.011

30. Raisi-Estabragh Z., Harvey N.C., Neubauer S., Petersen S.E. Cardiovascular magnetic resonance imaging in the UK Biobank: a major international health research resource. Eur. Heart J. Cardiovasc. Imaging. 2021;22(3):251–258. doi: 10.1093/ehjci/jeaa297

31. Aung N., Bartoli A., Rauseo E., Cortaredona S., Sanghvi M.M., Fournel J., Ghattas B., Khanji M.Y., Petersen S.E., Jacquier A. Left ventricular trabeculations at cardiac mri: reference ranges and association with cardiovascular risk factors in UK Biobank. Radiology. 2024;311(1):e232455. doi: 10.1148/radiol.232455

32. Woodbridge S.P., Aung N., Paiva J.M., Sanghvi M.M., Zemrak F., Fung K., Petersen S.E. Physical activity and left ventricular trabeculation in the UK Biobank community-based cohort study. Heart. 2019;105(13):990–998. doi: 10.1136/heartjnl-2018-314155

33. Kwan A.C., Chang E.W., Jain I., Theurer J., Tang X., Francisco N., Haddad F., Liang D., Fábián A., Ferencz A., … Ouyang D. Deep learningderived myocardial strain. JACC Cardiovasc. Imaging. 2024;17(7):715–725. doi: 10.1016/j.jcmg.2024.01.011

34. Liu B., Chang H., Yang D., Yang F., Wang Q., Deng Y., Li L., Lv W., Zhang B., Yu L., Burkhoff D., He K. A deep learning framework assisted echocardiography with diagnosis, lesion localization, phenogrouping heterogeneous disease, and anomaly detection. Sci. Rep. 2023;13(1):3. doi: 10.1038/s41598-022-27211-w

35. Ghorbani A., Ouyang D., Abid A., He B., Chen J.H., Harrington R.A., Liang D.H., Ashley E.A., Zou J.Y. Deep learning interpretation of echocardiograms. NPJ Digit. Med. 2020;3(1):10. doi: 10.1038/s41746-019-0216-8.