Top

Published in:

Open Access 18-08-2023 | Artificial Intelligence | Cardiac

Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking—a cardiovascular MR study in health and disease

Authors: Jan Gröschel, Johanna Kuhnt, Darian Viezzer, Thomas Hadler, Sophie Hormes, Phillip Barckow, Jeanette Schulz-Menger, Edyta Blaszczyk

Published in: European Radiology | Issue 2/2024

Abstract

Objectives

The analysis of myocardial deformation using feature tracking in cardiovascular MR allows for the assessment of global and segmental strain values. The aim of this study was to compare strain values derived from artificial intelligence (AI)–based contours with manually derived strain values in healthy volunteers and patients with cardiac pathologies.

Materials and methods

A cohort of 136 subjects (60 healthy volunteers and 76 patients; of those including 46 cases with left ventricular hypertrophy (LVH) of varying etiology and 30 cases with chronic myocardial infarction) was analyzed. Comparisons were based on quantitative strain analysis and on a geometric level by the Dice similarity coefficient (DSC) of the segmentations. Strain quantification was performed in 3 long-axis slices and short-axis (SAX) stack with epi- and endocardial contours in end-diastole. AI contours were checked for plausibility and potential errors in the tracking algorithm.

Results

AI-derived strain values overestimated radial strain (+ 1.8 ± 1.7% (mean difference ± standard deviation); p = 0.03) and underestimated circumferential (− 0.8 ± 0.8%; p = 0.02) and longitudinal strain (− 0.1 ± 0.8%; p = 0.54). Pairwise group comparisons revealed no significant differences for global strain. The DSC showed good agreement for healthy volunteers (85.3 ± 10.3% for SAX) and patients (80.8 ± 9.6% for SAX). In 27 cases (27/76; 35.5%), a tracking error was found, predominantly (24/27; 88.9%) in the LVH group and 22 of those (22/27; 81.5%) at the insertion of the papillary muscle in lateral segments.

Conclusions

Strain analysis based on AI-segmented images shows good results in healthy volunteers and in most of the patient groups. Hypertrophied ventricles remain a challenge for contouring and feature tracking.

Clinical relevance statement

AI-based segmentations can help to streamline and standardize strain analysis by feature tracking.

Key Points

• Assessment of strain in cardiovascular magnetic resonance by feature tracking can generate global and segmental strain values.

• Commercially available artificial intelligence algorithms provide segmentation for strain analysis comparable to manual segmentation.

• Hypertrophied ventricles are challenging in regards of strain analysis by feature tracking.

Available only for authorised users

Korosoglou G, Giusca S, Hofmann NP et al (2019) Strain-encoded magnetic resonance: a method for the assessment of myocardial deformation. ESC Heart Fail 6:584–602. https://doi.org/10.1002/ehf2.12442CrossRefPubMedPubMedCentral

Kim D, Gilson WD, Kramer CM, Epstein FH (2004) Myocardial tissue tracking with two-dimensional cine displacement-encoded MR imaging: development and initial evaluation. Radiology 230:862–871. https://doi.org/10.1148/radiol.2303021213CrossRefPubMed

Bucius P, Erley J, Tanacli R et al (2020) Comparison of feature tracking, fast-SENC, and myocardial tagging for global and segmental left ventricular strain. ESC Heart Fail 7:523–532. https://doi.org/10.1002/ehf2.12576CrossRefPubMed

Lapinskas T, Zieschang V, Erley J et al (2019) Strain-encoded cardiac magnetic resonance imaging: a new approach for fast estimation of left ventricular function. BMC Cardiovasc Disord 19:52. https://doi.org/10.1186/s12872-019-1031-5CrossRefPubMedPubMedCentral

Liu B, Dardeer AM, Moody WE et al (2018) Reference ranges for three-dimensional feature tracking cardiac magnetic resonance: comparison with two-dimensional methodology and relevance of age and gender. Int J Cardiovasc Imaging 34:761–775. https://doi.org/10.1007/s10554-017-1277-xCrossRefPubMed

Jolly M-P, Jordan JH, Meléndez GC et al (2017) Automated assessments of circumferential strain from cine CMR correlate with LVEF declines in cancer patients early after receipt of cardio-toxic chemotherapy. J Cardiovasc Magn Reson 19:59. https://doi.org/10.1186/s12968-017-0373-3CrossRefPubMedPubMedCentral

Barbosa MF, Fusco DR, Gaiolla RD et al (2021) Characterization of subclinical diastolic dysfunction by cardiac magnetic resonance feature-tracking in adult survivors of non-Hodgkin lymphoma treated with anthracyclines. BMC Cardiovasc Disord 21:170. https://doi.org/10.1186/s12872-021-01996-6CrossRefPubMedPubMedCentral

Eitel I, Stiermaier T, Lange T et al (2018) Cardiac magnetic resonance myocardial feature tracking for optimized prediction of cardiovascular events following myocardial infarction. JACC Cardiovasc Imaging 11:1433–1444. https://doi.org/10.1016/j.jcmg.2017.11.034CrossRefPubMed

Lange T, Stiermaier T, Backhaus SJ et al (2021) Functional and prognostic implications of cardiac magnetic resonance feature tracking-derived remote myocardial strain analyses in patients following acute myocardial infarction. Clin Res Cardiol 110:270–280. https://doi.org/10.1007/s00392-020-01747-1CrossRefPubMed

10.

Wamil M, Borlotti A, Liu D et al (2019) Combined T1-mapping and tissue tracking analysis predicts severity of ischemic injury following acute STEMI—an Oxford Acute Myocardial Infarction (OxAMI) study. Int J Cardiovasc Imaging 35:1297–1308. https://doi.org/10.1007/s10554-019-01542-8CrossRefPubMedPubMedCentral

11.

Nucifora G, Muser D, Gianfagna P et al (2015) Systolic and diastolic myocardial mechanics in hypertrophic cardiomyopathy and their link to the extent of hypertrophy, replacement fibrosis and interstitial fibrosis. Int J Cardiovasc Imaging 31:1603–1610. https://doi.org/10.1007/s10554-015-0720-0CrossRefPubMed

12.

Bogarapu S, Puchalski MD, Everitt MD et al (2016) Novel cardiac magnetic resonance feature tracking (CMR-FT) analysis for detection of myocardial fibrosis in pediatric hypertrophic cardiomyopathy. Pediatr Cardiol 37:663–673. https://doi.org/10.1007/s00246-015-1329-8CrossRefPubMed

13.

Baeßler B, Schaarschmidt F, Dick A et al (2016) Diagnostic implications of magnetic resonance feature tracking derived myocardial strain parameters in acute myocarditis. Eur J Radiol 85:218–227. https://doi.org/10.1016/j.ejrad.2015.11.023CrossRefPubMed

14.

Weigand J, Nielsen JC, Sengupta PP et al (2016) Feature tracking-derived peak systolic strain compared to late gadolinium enhancement in troponin-positive myocarditis: a case-control study. Pediatr Cardiol 37:696–703. https://doi.org/10.1007/s00246-015-1333-zCrossRefPubMed

15.

Lim C, Blaszczyk E, Riazy L et al (2020) Quantification of myocardial strain assessed by cardiovascular magnetic resonance feature tracking in healthy subjects-influence of segmentation and analysis software. Eur Radiol. https://doi.org/10.1007/s00330-020-07539-5CrossRefPubMedPubMedCentral

16.

Backhaus SJ, Metschies G, Billing M et al (2019) Cardiovascular magnetic resonance imaging feature tracking: impact of training on observer performance and reproducibility. PLoS One 14:e0210127. https://doi.org/10.1371/journal.pone.0210127

17.

Backhaus SJ, Aldehayat H, Kowallick JT et al (2022) Artificial intelligence fully automated myocardial strain quantification for risk stratification following acute myocardial infarction. Sci Rep 12:12220. https://doi.org/10.1038/s41598-022-16228-wCrossRefPubMedPubMedCentralADS

18.

Ruijsink B, Puyol-Antón E, Oksuz I et al (2020) Fully automated, quality-controlled cardiac analysis from CMR: validation and large-scale application to characterize cardiac function. JACC Cardiovasc Imaging 13:684–695. https://doi.org/10.1016/j.jcmg.2019.05.030CrossRefPubMed

19.

von Knobelsdorff-Brenkenhoff F, Hennig P, Menza M et al (2016) Myocardial dysfunction in patients with aortic stenosis and hypertensive heart disease assessed by MR tissue phase mapping. J Magn Reson Imaging 44:168–177. https://doi.org/10.1002/jmri.25125

20.

Prothmann M, von Knobelsdorff-Brenkenhoff F, Töpper A et al (2016) High spatial resolution cardiovascular magnetic resonance at 7.0 Tesla in patients with hypertrophic cardiomyopathy - first experiences: lesson learned from 7.0 Tesla. PLoS One 11:e0148066. https://doi.org/10.1371/journal.pone.0148066

21.

Gröschel J, Ammann C, Zange L et al (2022) Fast acquisition of left and right ventricular function parameters applying cardiovascular magnetic resonance in clinical routine - validation of a 2-shot compressed sensing cine sequence. Scand Cardiovasc J 56:266–275. https://doi.org/10.1080/14017431.2022.2099010

22.

Petersen SE, Matthews PM, Francis JM et al (2016) UK Biobank’s cardiovascular magnetic resonance protocol. J Cardiovasc Magn Reson 18:8. https://doi.org/10.1186/s12968-016-0227-4

23.

Bistoquet A, Oshinski J, Skrinjar O (2007) Left ventricular deformation recovery from cine MRI using an incompressible model. IEEE Trans Med Imaging 26:1136–1153. https://doi.org/10.1109/TMI.2007.903693CrossRefPubMed

24.

Bistoquet A, Oshinski J, Skrinjar O (2008) Myocardial deformation recovery from cine MRI using a nearly incompressible biventricular model. Med Image Anal 12:69–85. https://doi.org/10.1016/j.media.2007.10.009CrossRefPubMed

25.

Selvadurai BSN, Puntmann VO, Bluemke DA et al (2018) Definition of left ventricular segments for cardiac magnetic resonance imaging. JACC Cardiovasc Imaging 11:926–928. https://doi.org/10.1016/j.jcmg.2017.09.010CrossRefPubMed

26.

Heinke R, Pathan F, Le M et al (2019) Towards standardized postprocessing of global longitudinal strain by feature tracking - OptiStrain CMR-FT study. BMC Cardiovasc Disord 19:267. https://doi.org/10.1186/s12872-019-1255-4CrossRefPubMedPubMedCentral

27.

Hadler T, Wetzl J, Lange S et al (2022) Introduction of Lazy Luna an automatic software-driven multilevel comparison of ventricular function quantification in cardiovascular magnetic resonance imaging. Sci Rep 12:6629. https://doi.org/10.1038/s41598-022-10464-wCrossRefPubMedPubMedCentralADS

28.

Petersen SE, Aung N, Sanghvi MM et al (2017) Reference ranges for cardiac structure and function using cardiovascular magnetic resonance (CMR) in Caucasians from the UK Biobank population cohort. J Cardiovasc Magn Reson 19:18. https://doi.org/10.1186/s12968-017-0327-9

29.

Schulz-Menger J, Bluemke DA, Bremerich J et al (2020) Standardized image interpretation and post-processing in cardiovascular magnetic resonance - 2020 update. J Cardiovasc Magn Reson 22:19. https://doi.org/10.1186/s12968-020-00610-6CrossRefPubMedPubMedCentral

30.

Bernard O, Lalande A, Zotti C et al (2018) Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging 37:2514–2525. https://doi.org/10.1109/TMI.2018.2837502CrossRefPubMed

31.

Andre F, Steen H, Matheis P et al (2015) Age- and gender-related normal left ventricular deformation assessed by cardiovascular magnetic resonance feature tracking. J Cardiovasc Magn Reson 17:25. https://doi.org/10.1186/s12968-015-0123-3

32.

Kim MY, Park EA, Lee W, Lee SP (2020) Cardiac magnetic resonance feature tracking in aortic stenosis: exploration of strain parameters and prognostic value in asymptomatic patients with preserved ejection fraction. Korean J Radiol 21:268–279. https://doi.org/10.3348/kjr.2019.0441CrossRefPubMedPubMedCentral

33.

Miskinyte E, Bucius P, Erley J et al (2019) Assessment of global longitudinal and circumferential strain using computed tomography feature tracking: intra-individual comparison with CMR feature tracking and myocardial tagging in patients with severe aortic stenosis. J Clin Med 8:E1423. https://doi.org/10.3390/jcm8091423CrossRef

34.

Al Musa T, Uddin A, Swoboda PP et al (2017) Myocardial strain and symptom severity in severe aortic stenosis: insights from cardiovascular magnetic resonance. Quant Imaging Med Surg 7:38–47. https://doi.org/10.21037/qims.2017.02.05CrossRefPubMedPubMedCentral

35.

Spath NB, Gomez M, Everett RJ et al (2019) Global Longitudinal strain analysis using cardiac MRI in aortic stenosis: comparison with left ventricular remodeling, myocardial fibrosis, and 2-year clinical outcomes. Radiol Cardiothorac Imaging 1:e190027. https://doi.org/10.1148/ryct.2019190027CrossRefPubMedPubMedCentral

36.

Neisius U, Myerson L, Fahmy AS et al (2019) Cardiovascular magnetic resonance feature tracking strain analysis for discrimination between hypertensive heart disease and hypertrophic cardiomyopathy. PLoS One 14:e0221061. https://doi.org/10.1371/journal.pone.0221061

37.

Gastl M, Lachmann V, Christidi A et al (2021) Cardiac magnetic resonance T2 mapping and feature tracking in athlete’s heart and HCM. Eur Radiol 31:2768–2777. https://doi.org/10.1007/s00330-020-07289-4CrossRefPubMed

38.

Harrigan CJ, Appelbaum E, Maron BJ et al (2008) Significance of papillary muscle abnormalities identified by cardiovascular magnetic resonance in hypertrophic cardiomyopathy. Am J Cardiol 101:668–673. https://doi.org/10.1016/j.amjcard.2007.10.032CrossRefPubMed

39.

Roberts WC, Cohen LS (1972) Left ventricular papillary muscles. Description of the normal and a survey of conditions causing them to be abnormal. Circulation 46:138–154. https://doi.org/10.1161/01.cir.46.1.138CrossRefPubMed

40.

Pedrizzetti G, Claus P, Kilner PJ, Nagel E (2016) Principles of cardiovascular magnetic resonance feature tracking and echocardiographic speckle tracking for informed clinical use. J Cardiovasc Magn Reson 18:51. https://doi.org/10.1186/s12968-016-0269-7CrossRefPubMedPubMedCentral

41.

Vogel-Claussen J, Finn JP, Gomes AS et al (2006) Left ventricular papillary muscle mass: relationship to left ventricular mass and volumes by magnetic resonance imaging. J Comput Assist Tomogr 30:426–432. https://doi.org/10.1097/00004728-200605000-00013CrossRefPubMed

42.

Wassmuth R, von Knobelsdorff-Brenkenhoff F, Gruettner H et al (2014) Cardiac magnetic resonance imaging of congenital bicuspid aortic valves and associated aortic pathologies in adults. Eur Heart J - Cardiovasc Imaging 15:673–679. https://doi.org/10.1093/ehjci/jet275CrossRefPubMed

43.

Rossi A, van der Linde D, Yap SC et al (2013) Ascending aorta dilatation in patients with bicuspid aortic valve stenosis: a prospective CMR study. Eur Radiol 23:642–649. https://doi.org/10.1007/s00330-012-2651-7CrossRefPubMed

44.

Morton G, Schuster A, Jogiya R et al (2012) Inter-study reproducibility of cardiovascular magnetic resonance myocardial feature tracking. J Cardiovasc Magn Reson 14:43. https://doi.org/10.1186/1532-429X-14-43

45.

Schmidt B, Dick A, Treutlein M et al (2017) Intra- and inter-observer reproducibility of global and regional magnetic resonance feature tracking derived strain parameters of the left and right ventricle. Eur J Radiol 89:97–105. https://doi.org/10.1016/j.ejrad.2017.01.025CrossRefPubMed

46.

Auger DA, Ghadimi S, Cai X et al (2022) Reproducibility of global and segmental myocardial strain using cine DENSE at 3 T: a multicenter cardiovascular magnetic resonance study in healthy subjects and patients with heart disease. J Cardiovasc Magn Reson 24:23. https://doi.org/10.1186/s12968-022-00851-7

47.

Lin K, Meng L, Collins JD et al (2017) Reproducibility of cine displacement encoding with stimulated echoes (DENSE) in human subjects. Magn Reson Imaging 35:148–153. https://doi.org/10.1016/j.mri.2016.08.009CrossRefPubMed

48.

Mangion K, Carrick D, Clerfond G et al (2019) Predictors of segmental myocardial functional recovery in patients after an acute ST-Elevation myocardial infarction. Eur J Radiol 112:121–129. https://doi.org/10.1016/j.ejrad.2019.01.010CrossRefPubMedPubMedCentral

49.

Neizel M, Lossnitzer D, Korosoglou G et al (2009) Strain-encoded (SENC) magnetic resonance imaging to evaluate regional heterogeneity of myocardial strain in healthy volunteers: comparison with conventional tagging. J Magn Reson Imaging 29:99–105. https://doi.org/10.1002/jmri.21612

50.

Giusca S, Korosoglou G, Zieschang V et al (2018) Reproducibility study on myocardial strain assessment using fast-SENC cardiac magnetic resonance imaging. Sci Rep 8:14100. https://doi.org/10.1038/s41598-018-32226-3CrossRefPubMedPubMedCentralADS

51.

Erley J, Zieschang V, Lapinskas T et al (2020) A multi-vendor, multi-center study on reproducibility and comparability of fast strain-encoded cardiovascular magnetic resonance imaging. Int J Cardiovasc Imaging 36:899–911. https://doi.org/10.1007/s10554-020-01775-yCrossRefPubMedPubMedCentral

52.

Korosoglou G, Giusca S, Montenbruck M et al (2021) Fast strain-encoded cardiac magnetic resonance for diagnostic classification and risk stratification of heart failure patients. JACC Cardiovasc Imaging 14:1177–1188. https://doi.org/10.1016/j.jcmg.2020.10.024CrossRefPubMed

53.

Kuetting DLR, Dabir D, Homsi R et al (2016) The effects of extracellular contrast agent (Gadobutrol) on the precision and reproducibility of cardiovascular magnetic resonance feature tracking. J Cardiovasc Magn Reson 18:30. https://doi.org/10.1186/s12968-016-0249-y

Title: Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking—a cardiovascular MR study in health and disease
Authors: Jan Gröschel
Johanna Kuhnt
Darian Viezzer
Thomas Hadler
Sophie Hormes
Phillip Barckow
Jeanette Schulz-Menger
Edyta Blaszczyk
Publication date: 18-08-2023
Publisher: Springer Berlin Heidelberg
Keyword: Artificial Intelligence
Published in: European Radiology / Issue 2/2024
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-023-10127-y

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking—a cardiovascular MR study in health and disease

Abstract

Objectives

Materials and methods

Results

Conclusions

Clinical relevance statement

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Materials and methods

Results

Conclusions

Clinical relevance statement

Key Points

Please log in to get access to this content

Other articles of this Issue 2/2024

3D fusion is superior to 2D point-to-point contrast-enhanced US to evaluate the ablative margin after RFA for hepatocellular carcinoma

Enhanced vessel wall magnetic resonance imaging in the follow-up of intracranial aneurysms treated with flow diversion

Radiological pulmonary sequelae after COVID-19 and correlation with clinical and functional pulmonary evaluation: results of a prospective cohort

Follow-up strategy of radiofrequency ablation for papillary thyroid microcarcinoma: defining a response-to-ablation system

Use of artificial intelligence in triaging of chest radiographs to reduce radiologists’ workload

Diagnostic performance of MRI for assessing axillary lymph node status after neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis