Top

Published in:

Open Access 01-12-2023 | Magnetic Resonance Imaging | Original Article

Multi-channel deep learning model-based myocardial spatial–temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH

Authors: Kaiyue Diao, Hong-qing Liang, Hong-kun Yin, Ming-jing Yuan, Min Gu, Peng-xin Yu, Sen He, Jiayu Sun, Bin Song, Kang Li, Yong He

Published in: Insights into Imaging | Issue 1/2023

Abstract

Background

To develop a fully automatic framework for the diagnosis of cause for left ventricular hypertrophy (LVH) via cardiac cine images.

Methods

A total of 302 LVH patients with cine MRI images were recruited as the primary cohort. Another 53 LVH patients prospectively collected or from multi-centers were used as the external test dataset. Different models based on the cardiac regions (Model 1), segmented ventricle (Model 2) and ventricle mask (Model 3) were constructed. The diagnostic performance was accessed by the confusion matrix with respect to overall accuracy. The capability of the predictive models for binary classification of cardiac amyloidosis (CA), hypertrophic cardiomyopathy (HCM) or hypertensive heart disease (HHD) were also evaluated. Additionally, the diagnostic performance of best Model was compared with that of 7 radiologists/cardiologists.

Results

Model 3 showed the best performance with an overall classification accuracy up to 77.4% in the external test datasets. On the subtasks for identifying CA, HCM or HHD only, Model 3 also achieved the best performance with AUCs yielding 0.895–0.980, 0.879–0.984 and 0.848–0.983 in the validation, internal test and external test datasets, respectively. The deep learning model showed non-inferior diagnostic capability to the cardiovascular imaging expert and outperformed other radiologists/cardiologists.

Conclusion

The combined model based on the mask of left ventricular segmented from multi-sequences cine MR images shows favorable and robust performance in diagnosing the cause of left ventricular hypertrophy, which could be served as a noninvasive tool and help clinical decision.

Available only for authorised users

Geske JB, Ommen SR, Gersh BJ (2018) Hypertrophic cardiomyopathy: clinical update. JACC Hear Fail 6:364–375. https://doi.org/10.1016/j.jchf.2018.02.010CrossRef

Farjo PD, Sengupta PP (2021) ECG for screening cardiac abnormalities: the premise and promise of machine learning. Circ Cardiovasc Imaging. https://doi.org/10.1161/CIRCIMAGING.121.012837CrossRefPubMed

Al-Mallah MH (2019) Radiomics in hypertrophic cardiomyopathy: the new tool. JACC Cardiovasc Imaging 12:1955–1957. https://doi.org/10.1016/j.jcmg.2019.02.004CrossRefPubMed

Kittleson MM, Maurer MS, Ambardekar AV et al (2020) Cardiac amyloidosis: evolving diagnosis and management: a scientific statement from the American heart association. Circulation. https://doi.org/10.1161/cir.0000000000000792CrossRefPubMed

Ferreira VM, Schulz-Menger J, Holmvang G et al (2018) Cardiovascular magnetic resonance in nonischemic myocardial inflammation: expert recommendations. J Am Coll Cardiol 72:3158–3176. https://doi.org/10.1016/j.jacc.2018.09.072CrossRefPubMed

Hinojar R, Varma N, Child N et al (2015) T1 mapping in discrimination of hypertrophic phenotypes: hypertensive heart disease and hypertrophic cardiomyopathy: findings from the international T1 multicenter cardiovascular magnetic resonance study. Circ Cardiovasc Imaging 8:1–9. https://doi.org/10.1161/CIRCIMAGING.115.003285CrossRef

Schulz-Menger J, Bluemke DA, Bremerich J et al (2020) Standardized image interpretation and post-processing in cardiovascular magnetic resonance—2020 update: society for cardiovascular magnetic resonance (SCMR): board of trustees task force on standardized post-processing. J Cardiovasc Magn Reson 22:19. https://doi.org/10.1186/s12968-020-00610-6CrossRefPubMedPubMedCentral

Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJ (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510. https://doi.org/10.1038/s41568-018-0016-5.ArtificialCrossRefPubMedPubMedCentral

Mjolsness E, DeCoste D (2001) Machine learning for science: State of the art and future prospects. Science 293:2051–2055. https://doi.org/10.1126/science.293.5537.2051CrossRefPubMed

10.

Xu B, Kocyigit D, Grimm R, Griffin BP, Cheng F (2020) Applications of artificial intelligence in multimodality cardiovascular imaging: a state-of-the-art review. Prog Cardiovasc Dis 63:367–376. https://doi.org/10.1016/j.pcad.2020.03.003CrossRefPubMed

11.

Badano LP, Keller DM, Muraru D, Torlasco C, Parati G (2020) Artificial intelligence and cardiovascular imaging: a win-win combination. Anatol J Cardiol 24:214–223. https://doi.org/10.14744/AnatolJCardiol.2020.94491CrossRefPubMedPubMedCentral

12.

Hannun AY, Rajpurkar P, Haghpanahi M et al (2019) Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 25:65–69. https://doi.org/10.1038/s41591-018-0268-3CrossRefPubMedPubMedCentral

13.

Zhang N, Yang G, Gao Z et al (2019) Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac cine MRI. Radiology 291:606–607. https://doi.org/10.1148/radiol.2019182304CrossRefPubMed

14.

Baskaran L, Maliakal G, Al’Aref SJ et al (2019) Identification and quantification of cardiovascular structures from CCTA: an end-to-end rapid pixel-wise deep-learning method. JACC Cardiovasc Imaging. https://doi.org/10.1016/j.jcmg.2019.08.025CrossRefPubMed

15.

Captur G, Manisty C, Moon JC (2016) Cardiac MRI evaluation of myocardial disease. Heart 102:1429–1435. https://doi.org/10.1136/heartjnl-2015-309077CrossRefPubMed

16.

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

17.

Mancia G, Fagard R, Narkiewicz K et al (2013) 2013 ESH/ESC guidelines for the management of arterial hypertension: the task force for the management of arterial hypertension of the European Society of Hypertension (ESH) and of the European Society of Cardiology (ESC). Eur Heart J 34:2159–2219. https://doi.org/10.1093/eurheartj/eht151CrossRefPubMed

18.

Zamorano JL, Anastasakis A, Borger MA et al (2014) 2014 ESC Guidelines on diagnosis and management of hypertrophic cardiomyopathy. Eur Heart J 35:2733–2779. https://doi.org/10.1093/eurheartj/ehu284CrossRef

19.

Cardim N, Galderisi M, Edvardsen T et al (2015) Role of multimodality cardiac imaging in the management of patients with hypertrophic cardiomyopathy: an expert consensus of the European Association of Cardiovascular Imaging Endorsed by the Saudi Heart Association. Eur Heart J Cardiovasc Imaging 16:280–280hh. https://doi.org/10.1093/ehjci/jeu291CrossRefPubMed

20.

DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837. https://doi.org/10.2307/2531595CrossRefPubMed

21.

Guarise A, Faccioli N, Foti G, Da Pozzo S, Meneghetti P, Morana G (2011) Ruolo dell’eco-cardiografia e della cardio-RM nella definizione dei rilievi morfologici e funzionali utili nella diagnosi di cardiomiopatia ipertrofica. Radiol Medica 116:197–210. https://doi.org/10.1007/s11547-010-0603-3CrossRef

22.

Pagourelias ED, Mirea O, Vovas G et al (2019) Relation of regional myocardial structure and function in hypertrophic cardiomyopathy and amyloidois: a combined two-dimensional speckle tracking and cardiovascular magnetic resonance analysis. Eur Heart J Cardiovasc Imaging 20:426–437. https://doi.org/10.1093/ehjci/jey107CrossRefPubMed

23.

Vigneault DM, Yang E, Jensen PJ et al (2019) Left ventricular strain is abnormal in preclinical and overt hypertrophic cardiomyopathy: cardiac MR feature tracking. Radiology 290:640–648. https://doi.org/10.1148/radiol.2018180339CrossRefPubMed

24.

Kawel-Boehm N, Hetzel SJ, Ambale-Venkatesh B et al (2020) Reference ranges (“normal values”) for cardiovascular magnetic resonance (CMR) in adults and children: 2020 update. J Cardiovasc Magn Reson 22:87. https://doi.org/10.1186/s12968-020-00683-3CrossRefPubMedPubMedCentral

25.

Thrall JH, Li X, Li Q et al (2018) Artificial intelligence and machine learning in radiology: opportunities, challenges, pitfalls, and criteria for success. J Am Coll Radiol 15:504–508. https://doi.org/10.1016/j.jacr.2017.12.026CrossRefPubMed

26.

Khurshid S, Friedman S, Pirruccello JP et al (2021) Deep learning to predict cardiac magnetic resonance-derived left ventricular mass and hypertrophy from 12-Lead ECGs. Circ Cardiovasc Imaging. https://doi.org/10.1161/CIRCIMAGING.120.012281CrossRefPubMedPubMedCentral

27.

Yu X, Yao X, Wu B et al (2021) Using deep learning method to identify left ventricular hypertrophy on echocardiography. Int J Cardiovasc Imaging. https://doi.org/10.1007/s10554-021-02461-3CrossRefPubMedPubMedCentral

28.

Kuruvilla S, Janardhanan R, Antkowiak P et al (2015) Increased extracellular volume and altered mechanics are associated with LVH in hypertensive heart disease, not hypertension alone. JACC Cardiovasc Imaging 8:172–180. https://doi.org/10.1016/j.jcmg.2014.09.020CrossRefPubMedPubMedCentral

29.

Neisius U, El-Rewaidy H, Nakamori S, Rodriguez J, Manning WJ, Nezafat R (2019) Radiomic analysis of myocardial native T1 imaging discriminates between hypertensive heart disease and hypertrophic cardiomyopathy. JACC Cardiovasc Imaging 12:1946–1954. https://doi.org/10.1016/j.jcmg.2018.11.024CrossRefPubMedPubMedCentral

30.

Martini N, Aimo A, Barison A et al (2020) Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance. J Cardiovasc Magn Reson 22:1–11. https://doi.org/10.1186/s12968-020-00690-4CrossRef

31.

Kotter E, Ranschaert E (2021) Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow. Eur Radiol 31:5–7. https://doi.org/10.1007/s00330-020-07148-2CrossRefPubMed

32.

Lachance CC, Walter M (2020) Artificial intelligence for classification of lung nodules: a review of clinical utility, diagnostic accuracy, cost-effectiveness, and guidelines. 1–23. PMID: 33074628

33.

Cao L, Shi R, Ge Y et al (2019) Fully automatic segmentation of type B aortic dissection from CTA images enabled by deep learning. Eur J Radiol 121:108713. https://doi.org/10.1016/j.ejrad.2019.108713CrossRefPubMed

34.

Ngo TA, Lu Z, Carneiro G (2017) Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance. Med Image Anal 35:159–171. https://doi.org/10.1016/j.media.2016.05.009CrossRefPubMed

35.

Bai W, Sinclair M, Tarroni G et al (2018) Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 20:1–12. https://doi.org/10.1186/s12968-018-0471-xCrossRef

36.

Tajbakhsh N, Jeyaseelan L, Li Q, Chiang JN, Wu Z, Ding X (2020) Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med Image Anal 63:101693. https://doi.org/10.1016/j.media.2020.101693CrossRefPubMed

Title: Multi-channel deep learning model-based myocardial spatial–temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH
Authors: Kaiyue Diao
Hong-qing Liang
Hong-kun Yin
Ming-jing Yuan
Min Gu
Peng-xin Yu
Sen He
Jiayu Sun
Bin Song
Kang Li
Yong He
Publication date: 01-12-2023
Publisher: Springer Vienna
Keywords: Magnetic Resonance Imaging
Magnetic Resonance Imaging
Artificial Intelligence
Cardiac Amyloidosis
Cardiac MRI
Published in: Insights into Imaging / Issue 1/2023
Electronic ISSN: 1869-4101
DOI: https://doi.org/10.1186/s13244-023-01401-0

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Multi-channel deep learning model-based myocardial spatial–temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH

Abstract

Background

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2023

New transperineal ultrasound-guided biopsy for men in whom PSA is increasing after Miles’ operation

Complications of cochlear implants with MRI scans in different body regions: type, frequency and impact

Best imaging signs identified by radiomics could outperform the model: application to differentiating lung carcinoid tumors from atypical hamartomas

Value of placental virtual magnetic resonance elastography and intravoxel incoherent motion-based diffusion and perfusion in predicting adverse outcomes of small-for-gestational-age infants

Generalizable transfer learning of automated tumor segmentation from cervical cancers toward a universal model for uterine malignancies in diffusion-weighted MRI

Technical aspects of inter-recti distance measurement with ultrasonographic imaging for physiotherapy purposes: the scoping review