Cine-cardiac magnetic resonance to distinguish between ischemic and non-ischemic cardiomyopathies: a machine learning approach.
Artificial intelligence
Cardiomyopathy
Cardiovascular diseases
Cine magnetic resonance imaging
Machine learning
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
07 Mar 2024
07 Mar 2024
Historique:
received:
26
08
2023
accepted:
15
01
2024
revised:
11
12
2023
medline:
7
3
2024
pubmed:
7
3
2024
entrez:
7
3
2024
Statut:
aheadofprint
Résumé
This work aimed to derive a machine learning (ML) model for the differentiation between ischemic cardiomyopathy (ICM) and non-ischemic cardiomyopathy (NICM) on non-contrast cardiovascular magnetic resonance (CMR). This retrospective study evaluated CMR scans of 107 consecutive patients (49 ICM, 58 NICM), including atrial and ventricular strain parameters. We used these data to compare an explainable tree-based gradient boosting additive model with four traditional ML models for the differentiation of ICM and NICM. The models were trained and internally validated with repeated cross-validation according to discrimination and calibration. Furthermore, we examined important variables for distinguishing between ICM and NICM. A total of 107 patients and 38 variables were available for the analysis. Of those, 49 were ICM (34 males, mean age 60 ± 9 years) and 58 patients were NICM (38 males, mean age 56 ± 19 years). After 10 repetitions of the tenfold cross-validation, the proposed model achieved the highest area under curve (0.82, 95% CI [0.47-1.00]) and lowest Brier score (0.19, 95% CI [0.13-0.27]), showing competitive diagnostic accuracy and calibration. At the Youden's index, sensitivity was 0.72 (95% CI [0.68-0.76]), the highest of all. Analysis of predictions revealed that both atrial and ventricular strain CMR parameters were important for the identification of ICM patients. The current study demonstrated that using a ML model, multi chamber myocardial strain, and function on non-contrast CMR parameters enables the discrimination between ICM and NICM with competitive diagnostic accuracy. A machine learning model based on non-contrast cardiovascular magnetic resonance parameters may discriminate between ischemic and non-ischemic cardiomyopathy enabling wider access to cardiovascular magnetic resonance examinations with lower costs and faster imaging acquisition. • The exponential growth in cardiovascular magnetic resonance examinations may require faster and more cost-effective protocols. • Artificial intelligence models can be utilized to distinguish between ischemic and non-ischemic etiologies. • Machine learning using non-contrast CMR parameters can effectively distinguish between ischemic and non-ischemic cardiomyopathies.
Identifiants
pubmed: 38451322
doi: 10.1007/s00330-024-10640-8
pii: 10.1007/s00330-024-10640-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Roth GA, Mensah GA, Johnson CO et al (2020) Global burden of cardiovascular diseases and risk factors, 1990–2019: Update From the GBD 2019 Study. J Am Coll Cardiol 76(25):2982–3021. https://doi.org/10.1016/j.jacc.2020.11.010
doi: 10.1016/j.jacc.2020.11.010
pubmed: 33309175
pmcid: 7755038
Khan MA, Hashim MJ, Mustafa H et al (2020) Global epidemiology of ischemic heart disease: results from the global burden of disease study. Cureus 12(7):e9349. https://doi.org/10.7759/cureus.9349
doi: 10.7759/cureus.9349
pubmed: 32742886
pmcid: 7384703
Maron BJ, Towbin JA, Thiene G et al (2006) Contemporary definitions and classification of the cardiomyopathies: an American Heart Association Scientific Statement from the Council on Clinical Cardiology, Heart Failure and Transplantation Committee; Quality of Care and Outcomes Research and Functi. Circulation 113(14):1807–1816. https://doi.org/10.1161/CIRCULATIONAHA.106.174287
doi: 10.1161/CIRCULATIONAHA.106.174287
pubmed: 16567565
Zeppenfeld K, Tfelt-Hansen J, de Riva M et al (2022) 2022 ESC Guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death: developed by the task force for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death of the European Society of Cardiology (ESC) Endorsed by the Association for European Paediatric and Congenital Cardiology (AEPC). Eur Heart J 43(40):3997–4126. https://doi.org/10.1093/eurheartj/ehac262
doi: 10.1093/eurheartj/ehac262
pubmed: 36017572
McDonagh TA, Metra M, Adamo M et al (2021) 2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: developed by the Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) With the special contributio. Eur Heart J 42(36):3599–3726. https://doi.org/10.1093/eurheartj/ehab368
doi: 10.1093/eurheartj/ehab368
pubmed: 34447992
Cau R, Solinas C, De Silva P et al. Role of cardiac MRI in the diagnosis of immune checkpoint inhibitor-associated myocarditis. Int J cancer. Published online June 2022. https://doi.org/10.1002/ijc.34169
Cau R, Bassareo P, Suri JS et al (2022) The emerging role of atrial strain assessed by cardiac MRI in different cardiovascular settings : an up-to-date review Feature tracking. (1)
Shanbhag SM, Greve AM, Aspelund T et al (2019) Prevalence and prognosis of ischaemic and non-ischaemic myocardial fibrosis in older adults. Eur Heart J 40(6):529–538. https://doi.org/10.1093/eurheartj/ehy713
doi: 10.1093/eurheartj/ehy713
pubmed: 30445559
Cau R, Pisu F, Suri JS et al (2023) Artificial intelligence applications in cardiovascular magnetic resonance imaging : are we on the path to avoiding the administration of contrast media? Published online 2023. Diagnostics 13(12):2061. https://doi.org/10.3390/diagnostics13122061
Avard E, Shiri I, Hajianfar G et al (2022) Non-contrast cine cardiac magnetic resonance image radiomics features and machine learning algorithms for myocardial infarction detection. Comput Biol Med 141:105145. https://doi.org/10.1016/j.compbiomed.2021.105145
doi: 10.1016/j.compbiomed.2021.105145
pubmed: 34929466
Larroza A, López-Lereu MP, Monmeneu JV et al (2018) Texture analysis of cardiac cine magnetic resonance imaging to detect nonviable segments in patients with chronic myocardial infarction. Med Phys 45(4):1471–1480. https://doi.org/10.1002/mp.12783
doi: 10.1002/mp.12783
pubmed: 29389013
Zhang Q, Burrage MK, Shanmuganathan M et al (2022) Artificial intelligence for contrast-free MRI: scar assessment in myocardial infarction using deep learning–based virtual native enhancement. Circulation 146(20):1492–1503. https://doi.org/10.1161/CIRCULATIONAHA.122.060137
doi: 10.1161/CIRCULATIONAHA.122.060137
pubmed: 36124774
pmcid: 9662825
Baessler B, Mannil M, Oebel S et al (2018) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 286(1):103–112
doi: 10.1148/radiol.2017170213
pubmed: 28836886
Baeßler B, Mannil M, Maintz D et al (2018) Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-Preliminary results. Eur J Radiol 102:61–67. https://doi.org/10.1016/j.ejrad.2018.03.013
doi: 10.1016/j.ejrad.2018.03.013
pubmed: 29685546
Fahmy AS, Rausch J, Neisius U et al (2018) Automated cardiac MR scar quantification in hypertrophic cardiomyopathy using deep convolutional neural networks. JACC Cardiovasc Imaging 11(12):1917–1918. https://doi.org/10.1016/j.jcmg.2018.04.030
doi: 10.1016/j.jcmg.2018.04.030
pubmed: 30121270
pmcid: 6286195
van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B (2020) Radiomics in medical imaging—“how-to” guide and critical reflection. Insights Imaging 11(1):91. https://doi.org/10.1186/s13244-020-00887-2
doi: 10.1186/s13244-020-00887-2
pubmed: 32785796
pmcid: 7423816
Chakraborti S, Maiti A, Pramanik S et al (2021) Evaluating the plausible application of advanced machine learnings in exploring determinant factors of present pandemic: a case for continent specific COVID-19 analysis. Sci Total Environ 765:142723. https://doi.org/10.1016/j.scitotenv.2020.142723
doi: 10.1016/j.scitotenv.2020.142723
pubmed: 33077215
Fay MP, Proschan MA (2010) Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Stat Surv 4:1–39. https://doi.org/10.1214/09-SS051
doi: 10.1214/09-SS051
pubmed: 20414472
pmcid: 2857732
DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3):837–845
doi: 10.2307/2531595
pubmed: 3203132
Mongan J, Moy L, Kahn CE (2020) Checklist for Artificial Intelligence in Medical Imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2(2):e200029. https://doi.org/10.1148/ryai.2020200029
doi: 10.1148/ryai.2020200029
pubmed: 33937821
pmcid: 8017414
Zhang N, Yang G, Gao Z et al (2019) Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac cine MRI. Radiology 291(3):606–617. https://doi.org/10.1148/RADIOL.2019182304
doi: 10.1148/RADIOL.2019182304
pubmed: 31038407
Cau R, Pisu F, Porcu M et al. Machine learning approach in diagnosing Takotsubo cardiomyopathy: the role of the combined evaluation of atrial and ventricular strain, and parametric mapping. Int J Cardiol. Published online November 2022. https://doi.org/10.1016/j.ijcard.2022.11.021
Larroza A, Materka A, López-Lereu MP, Monmeneu JV, Bodí V, Moratal D (2017) Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging. Eur J Radiol 92:78–83. https://doi.org/10.1016/j.ejrad.2017.04.024
doi: 10.1016/j.ejrad.2017.04.024
pubmed: 28624024
Zuo H, Zhang Y, Ma F et al (2020) Myocardial deformation pattern differs between ischemic and non-ischemic dilated cardiomyopathy: the diagnostic value of longitudinal strains. Ultrasound Med Biol 46(2):233–243. https://doi.org/10.1016/j.ultrasmedbio.2019.10.006
doi: 10.1016/j.ultrasmedbio.2019.10.006
pubmed: 31718811
Miric D, Barac A, Capkun V, Bakovic D (2021) Right ventricular free wall strain in acutely decompensated heart failure patients with ischemic and non-ischemic cardiomyopathy. Echocardiography 38(10):1747–1753. https://doi.org/10.1111/echo.15205
doi: 10.1111/echo.15205
pubmed: 34555211
Braunwald E (2013) Heart failure. JACC Heart Fail 1(1):1–20. https://doi.org/10.1016/j.jchf.2012.10.002
doi: 10.1016/j.jchf.2012.10.002
pubmed: 24621794
Cau R, Bassareo P, Cademartiri F et al (2023) Epicardial fat volume assessed with cardiac magnetic resonance imaging in patients with Takotsubo cardiomyopathy. Eur J Radiol 160:110706. https://doi.org/10.1016/j.ejrad.2023.110706
doi: 10.1016/j.ejrad.2023.110706
pubmed: 36701825
Scatteia A, Baritussio A, Bucciarelli-Ducci C (2017) Strain imaging using cardiac magnetic resonance. Heart Fail Rev 22(4):465–476. https://doi.org/10.1007/s10741-017-9621-8
doi: 10.1007/s10741-017-9621-8
pubmed: 28620745
pmcid: 5487809
Nagao M, Hatakenaka M, Matsuo Y et al (2012) Subendocardial contractile impairment in chronic ischemic myocardium: assessment by strain analysis of 3T tagged CMR. J Cardiovasc Magn Reson 14(1):14. https://doi.org/10.1186/1532-429X-14-14
doi: 10.1186/1532-429X-14-14
pubmed: 22300290
pmcid: 3286365
Stanton T, Marwick TH (2010) Assessment of subendocardial structure and function. JACC Cardiovasc Imaging 3(8):867–875. https://doi.org/10.1016/j.jcmg.2010.05.011
doi: 10.1016/j.jcmg.2010.05.011
pubmed: 20705269
Tian F, Gu Y, Zhang Y et al (2022) Evaluation of right ventricular myocardial mechanics by 2- and 3-dimensional speckle-tracking echocardiography in patients with an ischemic or non-ischemic etiology of end-stage heart failure. Front Cardiovasc Med 9:765191. https://doi.org/10.3389/fcvm.2022.765191
doi: 10.3389/fcvm.2022.765191
pubmed: 35694662
pmcid: 9174453
Tigen K, Karaahmet T, Dundar C et al (2015) Right ventricular and atrial functions in patients with nonischemic dilated cardiomyopathy. Wien Klin Wochenschr 127(21):877–883. https://doi.org/10.1007/s00508-015-0852-1
doi: 10.1007/s00508-015-0852-1
pubmed: 26377175
Mouton S, Ridon H, Fertin M et al (2017) 2D-speckle tracking right ventricular strain to assess right ventricular systolic function in systolic heart failure. Analysis of the right ventricular free and posterolateral walls. Int J Cardiol. 245:190–195. https://doi.org/10.1016/j.ijcard.2017.07.077
doi: 10.1016/j.ijcard.2017.07.077
pubmed: 28768580
Fang F, Lee AP, Yu CM (2014) Left atrial function in heart failure with impaired and preserved ejection fraction. Curr Opin Cardiol 29(5):430–436. https://doi.org/10.1097/HCO.0000000000000091
doi: 10.1097/HCO.0000000000000091
pubmed: 25032726
D’Andrea A, Caso P, Romano S et al (2009) Association between left atrial myocardial function and exercise capacity in patients with either idiopathic or ischemic dilated cardiomyopathy: a two-dimensional speckle strain study. Int J Cardiol 132(3):354–363. https://doi.org/10.1016/j.ijcard.2007.11.102
doi: 10.1016/j.ijcard.2007.11.102
pubmed: 18255178
Cau R, Bassareo P, Caredda G, et al. Atrial strain by feature-tracking cardiac magnetic resonance imaging in Takotsubo cardiomyopathy. features, feasibility, and reproducibility. Can Assoc Radiol J = J l’Association Can des Radiol. Published online October 2021:8465371211042497. https://doi.org/10.1177/08465371211042497