Skip to main content
SpringerLink
Log in

Detection of myocardial infarction based on novel deep transfer learning methods for urban healthcare in smart cities

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

One of the common cardiac disorders is a cardiac attack called Myocardial infarction (MI), which occurs due to the blockage of one or more coronary arteries. Timely treatment of MI is important and slight delay results in severe consequences. Electrocardiogram (ECG) is the main diagnostic tool to monitor and reveal the MI signals. The complex nature of MI signals along with noise poses challenges to doctors for accurate and quick diagnosis. Manually studying large amounts of ECG data can be tedious and time-consuming. Therefore, there is a need for methods to automatically analyze the ECG data and make diagnosis. Number of studies has been presented to address MI detection, but most of these methods are computationally expensive and faces the problem of overfitting while dealing real data. In this paper, an effective computer-aided diagnosis (CAD) system is presented to detect MI signals using the convolution neural network (CNN) for urban healthcare in smart cities. Two types of transfer learning techniques are employed to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed feature extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the VGG-MI1 model, the last layer of the VGG-Net model is replaced with a specific layer according to our requirements and various functions are optimized to reduce overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is selected as a feature descriptor of the ECG images to describe it with informative features. Considering the limited availability of dataset, ECG data is augmented which has increased the classification performance. A standard well-known database Physikalisch-Technische Bundesanstalt (PTB) Diagnostic ECG is used for the validation of the proposed framework. It is evident from experimental results that the proposed framework achieves a high accuracy surpasses the existing methods. In terms of accuracy, sensitivity, and specificity; VGG-MI1 achieved 99.02%, 98.76%, and 99.17%, respectively, while VGG-MI2 models achieved an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Acharya UR, Fujita H, Sudarshan VK, Shu LO, Adam M, Koh JEW et al (2016) Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads. Knowl-Based Syst 99:146–156

    Article  Google Scholar 

  2. Acharya UR, Fujita H, Lih OS, Hagiwara Y, Tan JH, Adam M (2017) Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci 415-416:190–198

    Article  Google Scholar 

  3. Al-Kindi SG, Ali F, Farghaly A, Nathani M, Tafreshi R (2011) Towards real-time detection of myocardial infarction by digital analysis of electrocardiograms. IEEE, 1st Middle East Conference on Biomedical Engineering, p.454–457

  4. Amrani M, Hammad M, Jiang F, Wang K, Amrani A (2018) Very deep feature extraction and fusion for arrhythmias detection. Neural Comput Applic 30(7):2047–2057

    Article  Google Scholar 

  5. Arif M, Malagore IA, Afsar FA (2012) Detection and localization of myocardial infarction using k-nearest neighbor classifier. J Med Syst 36(1):279–289

    Article  Google Scholar 

  6. Bousseljot R, Kreiseler D, Schnabel, A (1995) Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik, Band 40, Ergänzungsband 1 S 317

  7. Bouvrie J (2007) Notes on convolutional neural network

  8. Cardiovascular disease, “World Heart Day” (2019) [Online]. Available: http://www.who.int/cardiovascular_diseases/world-heart-day/en/. Accessed: 30-Jan-2019.

  9. Chang PC, Lin JJ, Hsieh JC, Weng J (2012) Myocardial infarction classification with multi-lead ECG using hidden markov models and gaussian mixture models. Appl Soft Comput 12(10):3165–3175

    Article  Google Scholar 

  10. Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. In Proc. British Mach Vis Conf (BMVC)

  11. Dan C, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. IEEE Comput Vis Pattern Recognit 157:3642–3649

    Google Scholar 

  12. Dohare AK, Kumar V, Kumar R (2018) Detection of myocardial infarction in 12 lead ECG using support vector machine. Appl Soft Comput 64:138–147

    Article  Google Scholar 

  13. Duda RO, Hart PE, Stork DG (2001) Pattern Classification 2nd Edition. Pattern classification. John Wiley and Sons, New York, pp 55–88

    Google Scholar 

  14. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE conference on computer vision and pattern recognition (CVPR). IEEE Comput Soc

  15. Hall J (2010) Guyton and Hall textbook of medical physiology: enhanced E-book: Elsevier Health Sciences

  16. Hammad M, Wang K (2017) Fingerprint classification based on a Q-Gaussian multiclass support vector machine. In: Proceedings of the 2017 international conference on biometrics engineering and application. ACM

  17. Hammad M, Wang K (2019) Parallel score fusion of ECG and fingerprint for human authentication based on convolution neural network. Comput Secur 81:107–122

    Article  Google Scholar 

  18. Hammad M, Maher A, Wang K, Jiang F, Amrani M (2018) Detection of abnormal heart conditions based on characteristics of ECG signals. Measurement 125:634–644

    Article  Google Scholar 

  19. Hammad M, Liu Y, Wang K (2018) Multimodal biometric authentication systems using convolution neural network based on different level fusion of ECG and fingerprint. IEEE Access 99:1–1. https://doi.org/10.1109/ACCESS.2018.2886573 Available from: https://ieeexplore.ieee.org/document/8575133/

    Article  Google Scholar 

  20. Hammad M, Zhang S, Wang K (2019) A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication. Futur Gener Comput Syst

  21. Han C, & Shi L (2019). ML–ResNet: a novel network to detect and locate myocardial infarction using 12 leads ECG. Comput Methods Prog Biomed 105138.

  22. Han C, Shi L (2019) Automated interpretable detection of myocardial infarction fusing energy entropy and morphological features. Comput Methods Prog Biomed 175:9–23

    Article  Google Scholar 

  23. Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31

    Article  Google Scholar 

  24. Janwe NJ, Bhoyar KK (2017) Multi-label semantic concept detection in videos using fusion of asymmetrically trained deep convolutional neural networks and foreground driven concept co-occurrence matrix. Appl Intell 48:2047

    Article  Google Scholar 

  25. Jayachandran ES, Joseph KP, Acharya UR (2010) Analysis of myocardial infarction using discrete wavelet transform. J Med Syst 34(6):985–992

    Article  Google Scholar 

  26. Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. arXiv:1408.5093v1 [preprint]. [cited 2014 Jun 20]: [4 p.]. Available from: https://arxiv.org/abs/1408.5093

  27. Jun TJ, Nguyen HM, Kang D, Kim D, Kim D, Kim YH (2018) ECG arrhythmia classification using a 2-d convolutional neural network. arXiv:1804.06812v1 [Preprint]. [cited 2018 Apr 18]: [22 p.]. Available from: https://arxiv.org/abs/1804.06812.

  28. Kligfield P (2018) Goldberger's clinical electrocardiography: a simplified approach, Ary L. Goldberger, Zachary D. Goldberger, Alexei Shvilkin. J Electrocardiol 51(4):620

    Article  Google Scholar 

  29. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Int Conf Neural Inf Proc Syst 60:1097–1105 Curran Associates Inc

    Google Scholar 

  30. Kumar M, Pachori RB, Acharya UR (2017) Automated diagnosis of myocardial infarction ECG signals using sample entropy in flexible analytic wavelet transform framework. Entropy 19(9):488. https://doi.org/10.3390/e19090488

    Article  Google Scholar 

  31. Liu B, Liu J, Wang G, Huang K, Li F, Zheng Y, Luo Y, Zhou F (2015) A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection. Comput Biol Med 61:178–184

    Article  Google Scholar 

  32. Liu W, Huang Q, Chang S, Wang H, He J (2018) Multiple-feature-branch convolutional neural network for myocardial infarction diagnosis using electrocardiogram. Biomed Signal Proc Control 45:22–32

    Article  Google Scholar 

  33. MathWorks, “Get Started with Transfer Learning”, (2019) [Online]. Available: https://www.mathworks.com/help/deeplearning/examples/get-started-with-transferlearning.html. Accessed: 30 Jan 2019

  34. Naser S, Dabanloo N, Attarodi G (2014) A new pattern recognition method for detection and localization of myocardial infarction using T-wave integral and Total integral as extracted features from one cycle of ECG signal. J Biomed Sci Eng 5(7):818–824

    Google Scholar 

  35. Nogueira RF, Lotufo RDA, Machado RC (2017) Fingerprint liveness detection using convolutional neural networks. IEEE Trans Inf Forensics Secur 11(6):1206–1213

    Article  Google Scholar 

  36. Oh SL, Vicnesh J, Ciaccio EJ, Yuvaraj R, Acharya UR (2019) Deep convolutional neural network model for automated diagnosis of schizophrenia using EEG signals. Appl Sci 9(14):2870

    Article  Google Scholar 

  37. Pan J, Tompkins WJ (1985) A real-time QRS detection algorithm. Biomed Eng IEEE Trans 32(3):230–236

    Article  Google Scholar 

  38. Paul JK, Iype T, Dileep R, Hagiwara Y, Koh JW, Acharya UR (2019). Characterization of fibromyalgia using sleep EEG signals with nonlinear dynamical features. Comput Biol Med 103331

  39. Pławiak P (2018) Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals. Swarm Evol Comput 39:192–208

    Article  Google Scholar 

  40. Pławiak P (2018) Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system. Expert Syst Appl 92:334–349

    Article  Google Scholar 

  41. Pławiak P, Acharya UR (2019) Novel deep genetic ensemble of classifiers for arrhythmia detection using ECG signals. Neural Comput & Applic:1–25

  42. Protopapadakis E, Voulodimos A, Doulamis A, Doulamis N, Stathaki T (2019) Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing. Appl Intell 49:2793–2806. https://doi.org/10.1007/s10489-018-01396-y

    Article  Google Scholar 

  43. Raghavendra U, Fujita H, Bhandary SV, Gudigar A, Tan JH, Acharya UR (2018) Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci 441:41–49

    Article  MathSciNet  Google Scholar 

  44. Rajput JS, Sharma M, Acharya UR (2019) Hypertension diagnosis index for discrimination of high-risk hypertension ECG signals using optimal orthogonal wavelet filter Bank. Int J Environ Res Public Health 16(21):4068

    Article  Google Scholar 

  45. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252

    Article  MathSciNet  Google Scholar 

  46. Sadhukhan D, Pal S, Mitra M (2018) Automated identification of myocardial infarction using harmonic phase distribution pattern of ECG data. IEEE Trans Instrum Meas 99:1–11

    Google Scholar 

  47. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article  Google Scholar 

  48. Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) OverFeat: integrated recognition, localization and detection using convolutional networks. In: Proceedings of ICLR

  49. Sharma LN, Tripathy RK, Dandapat S (2015) Multiscale energy and eigenspace approach to detection and localization of myocardial infarction. IEEE Trans Biomed Eng 62(7):1827–1837

    Article  Google Scholar 

  50. Sharma M, Tan RS, Acharya UR (2018) A novel automated diagnostic system for classification of myocardial infarction ECG signals using an optimal biorthogonal filter bank. Comput Biol Med 102:341–356

    Article  Google Scholar 

  51. Sharma M, Singh S, Kumar A, San Tan R, Acharya UR (2019) Automated detection of shockable and non-shockable arrhythmia using novel wavelet-based ECG features. Comput Biol Med 115:103446

    Article  Google Scholar 

  52. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  Google Scholar 

  53. Strom JB, Tanguturi VK, Nagueh SF, Klein AL, Manning WJ (2019) Demonstrating the value of outcomes in echocardiography: imaging-based registries in improving patient care. J Am Soc Echocardiogr

  54. Sun L, Lu Y, Yang K, Li S (2012) ECG analysis using multiple instance learning for myocardial infarction detection. IEEE Trans Biomed Eng 59(12):3348–3356

    Article  Google Scholar 

  55. Sun J, Cai X, Sun F, Zhang J (2016) Scene image classification method based on Alex-Net model. IEEE, 2016 3rd International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

  56. Thygesen K, Alpert JS, Jaffe AS, Simoons ML, Chaitman BR, White HD (2012) Third universal definition of myocardial infarction. Circulation. 126(16):2020–2035

    Article  Google Scholar 

  57. Tsai DY, Kojima K (2005) Measurements of texture features of medical images and its application to computer-aided diagnosis in cardiomyopathy. Measurement. 37(3):284–292

    Article  Google Scholar 

  58. Tuncer T, Dogan S, Pławiak P, Acharya UR (2019) Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals. Knowl.-Based Syst 104923

  59. Velasco JM, Garnica O, Contador S, Lanchares J, Maqueda E, Botella M, et al. (2017) Data augmentation and evolutionary algorithms to improve the prediction of blood glucose levels in scarcity of training data. IEEE Congress on Evolutionary Computation (CEC)

  60. Wang Z, Qian L, Han C, Shi L (2020) Application of multi-feature fusion and random forests to the automated detection of myocardial infarction. Cogn Syst Res 59:15–26

    Article  Google Scholar 

  61. Wu JF, Bao YL, Chan SC, Wu HC, Zhang L, Wei XG (2017) Myocardial infarction detection and classification — A new multi-scale deep feature learning approach. IEEE Int Conf Digit Signal Proc 309–313

  62. Yıldırım Ö, Pławiak P, Tan RS, Acharya UR (2018) Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med 102:411–420

    Article  Google Scholar 

  63. Zeng K, Ding S, Jia W (2019) Single image super-resolution using a polymorphic parallel CNN. Appl Intell 49:292–300. https://doi.org/10.1007/s10489-018-1270-7

    Article  Google Scholar 

Download references

Acknowledgments

This project was funded by University of Jeddah, Jeddah, Saudi Arabia (Project number: UJ-02-018-ICGR). The authors, therefore, gratefully acknowledge DSR technical and financial support. Also, Ahmed A. Abd El-Latif acknowledges support from TYSP-Talented Young Scientist Program (China) and Menoufia University (Egypt). Additionally, the authors warmly thank their families for their unconditional support.

Author information

Authors and Affiliations

  1. Department of Cybersecurity, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia

    Ahmed Alghamdi

  2. Information Technology Department, Faculty of Computers and Information, Menoufia University, Shibin el Kom, Egypt

    Mohamed Hammad

  3. Centre for Visual Computing, University of Bradford, Bradford, BD7 1DP, UK

    Hassan Ugail

  4. Public health and Community Medicine Department, Faculty of Medicine, Menoufia University, Shebin El-Koom, Egypt

    Asmaa Abdel-Raheem

  5. Intelligent Media Lab, Department of Software, Sejong University, Seoul, Republic of Korea

    Khan Muhammad

  6. Computer Science Department, Misr Higher Institute of Commerce and Computers, Mansoura, Egypt

    Hany S. Khalifa

  7. Mathematics and Computer Science Department, Faculty of Science, Menoufia University, Shebin El-Koom, Egypt

    Ahmed A. Abd El-Latif

  8. School of Information Technology and Computer Science, Nile University, Giza, Egypt

    Ahmed A. Abd El-Latif

  9. School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150080, China

    Ahmed A. Abd El-Latif

Authors
  1. Ahmed Alghamdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohamed Hammad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hassan Ugail
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Asmaa Abdel-Raheem
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Khan Muhammad
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hany S. Khalifa
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ahmed A. Abd El-Latif
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ahmed A. Abd El-Latif.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Alghamdi, A., Hammad, M., Ugail, H. et al. Detection of myocardial infarction based on novel deep transfer learning methods for urban healthcare in smart cities. Multimed Tools Appl 83, 14913–14934 (2024). https://doi.org/10.1007/s11042-020-08769-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-08769-x

Keywords

Search

Navigation