Top

The International Journal of Cardiovascular Imaging

Published in:

Open Access 07-11-2024 | Myocarditis | Original Paper

Deep learning automatically distinguishes myocarditis patients from normal subjects based on MRI

Authors: Cosmin-Andrei Hatfaludi, Aurelian Roșca, Andreea Bianca Popescu, Teodora Chitiboi, Puneet Sharma, Theodora Benedek, Lucian Mihai Itu

Published in: The International Journal of Cardiovascular Imaging | Issue 12/2024

Abstract

Myocarditis, characterized by inflammation of the myocardial tissue, presents substantial risks to cardiovascular functionality, potentially precipitating critical outcomes including heart failure and arrhythmias. This investigation primarily aims to identify the optimal cardiovascular magnetic resonance imaging (CMRI) views for distinguishing between normal and myocarditis cases, using deep learning (DL) methodologies. Analyzing CMRI data from a cohort of 269 individuals, with 231 confirmed myocarditis cases and 38 as control participants, we implemented an innovative DL framework to facilitate the automated detection of myocarditis. Our approach was divided into single-frame and multi-frame analyses to evaluate different views and types of acquisitions for optimal diagnostic accuracy. The results demonstrated a weighted accuracy of 96.9%, with the highest accuracy achieved using the late gadolinium enhancement (LGE) 2-chamber view, underscoring the potential of DL in distinguishing myocarditis from normal cases on CMRI data.

Sagar S, Liu PP, Cooper LT (2012) Myocarditis Lancet 379(9817):738–747CrossRefPubMed

Kytö V, Saukko P, Lignitz E, Schwesinger G, Henn V, Saraste A et al (2005) Diagnosis and presentation of fatal myocarditis. Hum Pathol 36(9):1003–1007CrossRefPubMed

Sharifrazi D, Alizadehsani R, Joloudari JH, Shamshirband S, Hussain S, Sani ZA et al (2020) CNN-KCL: automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering

Asher A (2017) A review of endomyocardial biopsy and current practice in England: out of date or underutilised. Br J Cardiol 24(3):108–112

Ammirati E, Frigerio M, Adler ED, Basso C, Birnie DH, Brambatti M et al (2020) Management of acute myocarditis and chronic inflammatory cardiomyopathy: an expert consensus document. Circ Heart Fail 13(11):e007405CrossRefPubMedPubMedCentral

Katti G, Ara SA, Shireen A (2011) Magnetic resonance imaging (MRI)–a review. Int J Dent Clin 3(1):65–70

Gannon MP, Schaub E, Grines CL, Saba SG (2019) State of the art: evaluation and prognostication of myocarditis using cardiac MRI. J Magnet Reson Imaging 49(7):e122–e131CrossRef

Abdar M, Nasarian E, Zhou X, Bargshady G, Wijayaningrum VN, Hussain S (2019) Performance improvement of decision trees for diagnosis of coronary artery disease using multi filtering approach. In: 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS): IEEE; pp. 26–30

Deng L, Yu D (2014) Deep learning: methods and applications. Found Trends^® Signal Process 7(3–4):197–387CrossRef

10.

Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst ;30

11.

Shoeibi A, Ghassemi N, Heras J, Rezaei M, Gorriz JM (2022) Automatic diagnosis of myocarditis in cardiac magnetic images using CycleGAN and deep PreTrained models. International work-conference on the interplay between natural and artificial computation: Springer; pp. 145–155

12.

Moravvej SV, Alizadehsani R, Khanam S, Sobhaninia Z, Shoeibi A, Khozeimeh F et al (2022) RLMD-PA: a reinforcement learning-based myocarditis diagnosis combined with a population-based algorithm for pretraining weights. Contrast Media & Molecular Imaging

13.

Patro S, Sahu KK (2015) Normalization: a preprocessing stage. arXiv Preprint arXiv :150306462

14.

Zeng X, Wong DF, Chao LS (2014) Constructing better classifier ensemble based on weighted accuracy and diversity measure. Sci World J

15.

Hoo ZH, Candlish J, Teare D (2017) What is an ROC curve? BMJ Publishing Group Ltd and the British Association for Accident

16.

Lobo JM, Jiménez-Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Global Ecol Biogeogr 17(2):145–151CrossRef

17.

Unal I (2017) Defining an optimal cut-point value in ROC analysis: an alternative approach. Computational and mathematical methods in medicine

18.

Wong HB, Lim GH (2011) Measures of diagnostic accuracy: sensitivity, specificity, PPV and NPV. Proc Singap Healthc 20(4):316–318CrossRef

19.

Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32–35CrossRefPubMed

20.

Imambi S, Prakash KB, Kanagachidambaresan G (2021) PyTorch. Programming with Tensor Flow: solution for edge computing applications. pp. 87–104

21.

Kumari R, Srivastava SK (2017) Machine learning: a review on binary classification. Int J Comput Appl ;160(7)

22.

Pratiwi H, Windarto AP, Susliansyah S, Aria RR, Susilowati S, Rahayu LK et al (2020) Sigmoid activation function in selecting the best model of artificial neural networks. J Phys: Conf Ser p. 012010

23.

Fushiki T (2011) Estimation of prediction error by using K-fold cross-validation. Stat Comput 21:137–146CrossRef

24.

Zhang Y, Xia Z, Joishi C, Rajan S (2018) Design and Demonstration of (AlxGal-x) 2 O 3/Ga 2 O 3 Double Heterostructure Field Effect Transistor (DHFET). In: 2018 76th Device Research Conference (DRC): IEEE; pp. 1–2

25.

Ruby U, Yendapalli V (2020) Binary cross entropy with deep learning technique for image classification. Int J Adv Trends Comput Sci Eng. ;9(10)

26.

Simonyan K, Vedaldi A, Zisserman A (2013) Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv Preprint arXiv :13126034

27.

Sabouri M, Hajianfar G, Hosseini Z, Amini M, Mohebi M, Ghaedian T et al (2023) Myocardial perfusion SPECT imaging radiomic features and machine learning algorithms for cardiac contractile pattern recognition. J Digit Imag 36(2):497–509CrossRef

28.

Hajianfar G, Sabouri M, Salimi Y, Amini M, Bagheri S, Jenabi E et al (2024) Artificial intelligence-based analysis of whole-body bone scintigraphy: the quest for the optimal deep learning algorithm and comparison with human observer performance. Z Medizin Phys 34(2):242–257CrossRef

29.

Sun X, Yin Y, Yang Q, Huo T (2023) Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives. Eur J Med Res 28(1):242CrossRefPubMedPubMedCentral

30.

Liu R, Wang M, Zheng T, Zhang R, Li N, Chen Z et al (2022) An artificial intelligence-based risk prediction model of myocardial infarction. BMC Bioinform 23(1):217CrossRef

31.

El Kaid A, Baïna K (2023) A systematic review of recent deep learning approaches for 3D human pose estimation. J Imag 9(12):275CrossRef

Title: Deep learning automatically distinguishes myocarditis patients from normal subjects based on MRI
Authors: Cosmin-Andrei Hatfaludi
Aurelian Roșca
Andreea Bianca Popescu
Teodora Chitiboi
Puneet Sharma
Theodora Benedek
Lucian Mihai Itu
Publication date: 07-11-2024
Publisher: Springer Netherlands
Keyword: Myocarditis
Published in: The International Journal of Cardiovascular Imaging / Issue 12/2024
Print ISSN: 1569-5794
Electronic ISSN: 1875-8312
DOI: https://doi.org/10.1007/s10554-024-03284-8

Evaluation of right ventricular mechanics using exercise echocardiography in asymptomatic patients with severe mitral stenosis

Mitral Valve Stenosis
Original Paper

Left versus right common carotid artery intima-media thickness: when sub-millimetric differences matter

Comment

Intramyocardial and intra-atrial courses in the right coronary artery: prevalence and characteristics

CT Angiography
Original Paper

Leveraging artificial intelligence in cardiovascular imaging to advance non-invasive coronary artery disease screening

Editorial

Dynamic contrast-enhanced MRA of the aorta using a Golden-angle RAdial Sparse Parallel (GRASP) sequence: comparison with conventional time-resolved cartesian MRA (TWIST)

Open Access
Original Paper

Pericardial adhesion and performance of hemodynamically significant constrictive pericarditis using cine magnetic resonance feature tracking

Heart Failure
Original Paper

Keynote series | Spotlight on menopause

Menopause
Video Series

Menopause can have a significant impact on the body, with effects ranging beyond the endocrine and reproductive systems. Learn about the broader systemic effects of menopause, so you can help patients in your clinics through the transition.

Launching: Thursday 12th December 2024

Prof. Martha Hickey

Dr. Claudia Barth

Dr. Samar El Khoudary

Developed by: Springer Medicine

A quick guide to ECGs

Electrocardiography
Training Course

Improve your ECG interpretation skills with this comprehensive, rapid, interactive course. Expert advice provides detailed feedback as you work through 50 ECGs covering the most common cardiac presentations to ensure your practice stays up to date.

PD Dr. Carsten W. Israel

Developed by: Springer Medizin

Start the cases

Keynote webinar | Spotlight on medication adherence

Webinar | 27-06-2024 | 18:00 (CEST)

Medication non-adherence is a major barrier to effective healthcare delivery; half of all patients do not follow their doctor’s recommendations or treatment plan.

Our experts explain the fundamentals with a practical discussion of how to manage non-adherence in two common scenarios: hypertension and asthma control.

Prof. Kevin Dolgin

Prof. Florian Limbourg

Prof. Anoop Chauhan

Developed by: Springer Medicine

Watch now

Keynote series | Spotlight on menopause

Springer Medicine

Abstract

Please log in to get access to this content