Non-contrast cine cardiac magnetic resonance radiomics for the prediction of left ventricular adverse remodeling in patients with ischemic cardiomyopathy: a pilot study

Background. Early detection of left ventricular adverse remodeling and its predictors can improve the accuracy of postoperative monitoring and optimize personalized treatment strategies for high-risk patients. A promising approach is radiomics – a high-level medical image processing method that converts imaging data into quantitative indicators for precise characterization of pathological tissue changes.

Aim: To investigate radiomic features prognostic value based on noncontrast cine cardiac magnetic resonance imaging (MRI) for assessing the risk of adverse left ventricular remodeling in patients with ischemic cardiomyopathy.

Material and Methods. This observational, cohort, retrospective, single-center study included patients (n = 44, 59.2 ± 8.1 years old) with an established diagnosis of ischemic cardiomyopathy (ICM) and indications for surgery. Preoperatively, all patients underwent cardiac MRI with according to clinical indications (to assess myocardial viability). In the early postoperative period and one year after surgery, all patients underwent echocardiography. The criterion for continued LV remodeling was an increase in end diastolic volume ≥10% one year after surgery according to echocardiography. Two study groups were formed: group 1 (n = 23) – patients with ICM without LV aneurysm, who underwent isolated coronary artery bypass grafting; group 2 (n = 21) – patients with ICM and LV aneurysm, who underwent coronary artery bypass grafting in combination with aneurysmectomy and LV plastic surgery. The control group included 28 patients without morphofunctional and structural changes in the LV myocardium according to contrast-enhanced cardiac MRI. Radiomics analysis was performed on noncontrast cine cardiac MRI images at end-diastole.

Results. Texture analysis was performed on 72 regions of interest in cine images, corresponding to areas of visually intact myocardium on post-contrast images in patients with ICM (n = 44) and to areas of myocardium in patients in the control group (n = 28). In a year after surgery, continued LV remodeling was detected in 12 patients: 6 patients in groups 1 and 2, respectively. The highest number of statistically significant features with high and moderate predictive ability were identified in the group of patients with ICM and LV aneurysm who underwent a combined procedure – coronary artery bypass graft combined with aneurysmectomy and LV reconstruction. In contrast, in the group of patients who underwent coronary artery bypass graft alone, radiomic features demonstrated low differentiating ability. The most significant radiomic features belong to the category of second-order features: GLRLM (Run Percentage), GLSZM (Zone Percentage) and GLDM (Dependence Non Uniformity Normalized).

Conclusion. Non-contrast cine cardiac MRI Radiomics is a promising tool for stratifying the risk of adverse LV remodeling in patients with ICM, particularly after combined surgical procedures. Further development and validation of these approaches may facilitate personalized patient management and improve long-term clinical outcomes.

1. Cohn J.N., Ferrari R., Sharpe N. Cardiac remodeling-concepts and clinical implications: a consensus paper from an International Forum on Cardiac Remodeling. Behalf of an International Forum on Cardiac Remodeling. J. Am. Coll. Cardiol. 2000;35(3):569–582. https://doi.org/10.1016/s0735-1097(99)00630-0

2. Aimo A., Gaggin H.K., Barison A., Emdin M., Januzzi J.L.Jr. Imaging, biomarker, and clinical predictors of cardiac remodeling in heart failure with reduced ejection fraction. JACC Heart Fail. 2019;7(9):782–794. https://doi.org/10.1016/j.jchf.2019.06.004

3. Xin A., Liu M., Chen T., Chen F., Qian G., Zhang Y. et al. Non-contrast cine cardiac magnetic resonance derived-radiomics for the prediction of left ventricular adverse remodeling in patients with ST-Segment elevation myocardial infarction. Korean J. Radiol. 2023;24(9):827–837. https://doi.org/10.3348/kjr.2023.0061

4. Legallois D., Hodzic A., Alexandre J., Dolladille C., Saloux E., Manrique A. et al. Definition of left ventricular remodelling following ST-elevation myocardial infarction: a systematic review of cardiac magnetic resonance studies in the past decade. Heart Fail. Rev. 2022;27(1):37–48. https://doi.org/10.1007/s10741-020-09975-3

5. Bière L., Donal E., Jacquier A., Croisille P., Genée O., Christiaens L. et al. A new look at left ventricular remodeling definition by cardiac imaging. Int. J. Cardiol. 2016;209:17–19. https://doi.org/10.1016/j.ijcard.2016.02.009

6. Reindl M., Reinstadler S.J., Tiller C., Feistritzer H.J., Kofler M., Brix A. et al. Prognosis-based definition of left ventricular remodeling after ST-elevation myocardial infarction. Eur. Radiol. 2019;29(5):2330–2339. https://doi.org/10.1007/s00330-018-5875-3

7. Rodriguez-Palomares J.F., Gavara J., Ferreira-González I., Valente F., Rios C., Rodríguez-García J. et al. Prognostic value of initial left ventricular remodeling in patients with reperfused STEMI. JACC Cardiovasc. Imaging. 2019;12(12):2445–2456. https://doi.org/10.1016/j.jcmg.2019.02.025

8. Maksimova A.S., Ussov W.Yu., Shelkovnikova T.A., Mochula O.V., Ryumshina N.I., Sykhareva A.E. et al. Cardiac MRI Radiomics: review. Siberian Journal of Clinical and Experimental Medicine. 2023;38(3): 13–22. (In Russ.). https://doi.org/10.29001/2073-8552-2023-39-3-13-22

9. Yue X., Cui J., Huang S., Liu W., Qi J., He K. et al. An interpretable radiomics-based machine learning model for predicting reverse left ventricular remodeling in STEMI patients using late gadolinium enhancement of myocardial scar. Eur. Radiol. 2025;35(10):6302–6312. https://doi.org/10.1007/s00330-025-11419-1

10. Castellaccio A., Almeida Arostegui N., Palomo Jiménez M., Quiñones Tapia D., Bret Zurita M., Vañó Galván E. Artificial intelligence in cardiovascular magnetic resonance imaging. Radiologia (Engl. Ed.). 2025;67(2):239–247. https://doi.org/10.1016/j.rxeng.2025.03.001

11. Avard E., Shiri I., Hajianfar G., Abdollahi H., Kalantari K.R., Houshmand G. et al. Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection. Comput. Biol. Med. 2022;141:105145. https://doi.org/10.1016/j.compbiomed.2021.105145

12. Maksimova A.S., Samatov D.S., Merzlikin B.S., Shelkovnikova T.A., Listratov A.I., Zavadovsky K.V. Potential use of radiomics analysis of cine-mode cardiac MRI to detect post-infarction lesions in the left ventricular myocardium. Digital Diagnostics. 2024;5(4):682–694. (In Russ.). https://doi.org/10.17816/DD630602

13. Lasode J., Chantaksinopas W., Khongwirotphan S., Chattranukulchai P., Vorasettakarnkij Y., Sriswasdi S. et al. Radiomics for differential diagnosis of ischemic and dilated cardiomyopathy using non-contrast-enhanced cine cardiac magnetic resonance imaging. Radiol. Med. 2025;130(5):650–661. https://doi.org/10.1007/s11547-025-01979-z

14. Zaitsev V.V., Safronov K.S., Konasov K.S., Bavshin T.R., Manokhin K.A., Obraztsova L.A. et al. Development of predictive models for differential diagnosis of hypertrophic cardiomyopathy.russian Journal of Cardiology. 2024;29(11):6130. (In Russ.). https://doi.org/10.15829/1560-4071-2024-6130

15. Amyar A., Al-Deiri D., Sroubek J., Kiang A., Ghanbari F., Nakamori S. et al. Radiomic cardiac MRI signatures for predicting ventriculararrhythmias in patients with nonischemic dilated cardiomyopathy. JACC Adv. 2025;4(4):101684. https://doi.org/10.1016/j.jacadv.2025.101684

16. Deng J., Zhou L., Liao B., Cai Q., Luo G., Zhou H., Tang H. Challenges in clinical translation of cardiac magnetic resonance imaging radiomics in non-ischemic cardiomyopathy: a narrative review. Cardiovasc. Diagn. Ther. 2024;14(6):1210–1227. https://doi.org/10.21037/cdt-24-138

17. Chen B.H., An D.A., He J., Wu C.W., Yue T., Wu R. et al. Myocardial extracellular volume fraction radiomics analysis for differentiation of reversible versus irreversible myocardial damage and prediction of left ventricular adverse remodeling after ST-elevation myocardial infarction. Eur. Radiol. 2021;31:504–514. https://doi.org/10.1007/s00330-020-07117-9

18. Chang S., Han K., Kwon Y., Kim L., Hwang S., Kim H. et al. T1 Mapbased radiomics for prediction of left ventricular reverse remodeling in patients with non-ischemic dilated cardiomyopathy. Korean J. Radiol. 2023;24:395–405. https://doi.org/10.3348/kjr.2023.0065