Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques

Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques Publisher

Sharifrazi D¹ ; Alizadehsani R² ; Izadi NH³ ; Roshanzamir M⁴ ; Shoeibi A⁵ ; Khozeimeh F² ; Sani FA⁶ ; Sani ZA⁷ ; Hussain S⁸ ; Harlapur C⁹ ; Gorriz JM^{10, 11} ; Zhang YD¹² ; Khosravi A² ; Nahavandi S² Show All Authors

Sharifrazi D¹
Alizadehsani R²
Izadi NH³
Roshanzamir M⁴
Shoeibi A⁵
Khozeimeh F²
Sani FA⁶
Sani ZA⁷
Hussain S⁸
Harlapur C⁹
Gorriz JM^{10, 11}
Zhang YD¹²
Khosravi A²
Nahavandi S²
Sarrafzadegan N^{13, 14}
Islam SMS^{15, 16, 17}

Show Affiliations

1. Department of Computer Engineering, School of Technical and Engineering, Islamic Azad University, Shiraz Branch, Shiraz, Iran
2. Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia
3. Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran
4. Department of Computer Engineering, Faculty of Engineering, Fasa University, Fasa, Iran
5. Data Science and Computational Intelligence Institute, University of Granada, Granada, Spain
6. Mashhad University of Medical Science, Mashhad, Iran
7. Department of Cardiac MRI, Omid Hospital, Tehran, Iran
8. System Administrator, Dibrugarh University, Assam, 786004, India
9. Emergency Department, Epworth Hospital, Geelong, Australia
10. Department of Signal Theory, Networking and Communications, Universidad de Granada, Spain
11. Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom
12. Department of Informatics, University of Leicester, Leicester, United Kingdom
13. Faculty of Medicine, SPPH, University of British Columbia, Vancouver, BC, Canada
14. Isfahan Cardiovascular Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Khorram Ave, Isfahan, Iran
15. Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Deakin University, Geelong, Australia
16. Cardiovascular Division, George Institute for Global Health, Newtown, Australia
17. Sydney Medical School, University of Sydney, Camperdown, Australia

Source: Human-centric Computing and Information Sciences Published:2024

Abstract

Hypertrophic cardiomyopathy (HCM), which can lead to serious cardiac problems, is often diagnosed using cardiovascular magnetic resonance (CMR) images obtained from patients. This research consisted in developing a deep learning technique to diagnose HCM, using a dataset consisting of 37,421 healthy and 21,846 HCM patients obtained over a period of two years. The proposed dataset is the largest publicly available CMR dataset for HCM diagnosis. Three experts inspected the images and determined whether each one showed a case of HCM or not. Novel data augmentation was used by employing color filtering. To classify the augmented images, a convolutional neural network (CNN) was designed and tuned. To the best of the authors’ knowledge, none of the existing studies have tackled HCM diagnosis based on CMR images, and this paper is the first one in this regard. Comparing the designed algorithm output with the experts’ opinions, the proposed method achieved accuracy of 98.53%, recall of 98.70%, and specificity of 95.21% on the augmented dataset. Experiments were also conducted with different optimizers and other methods of data augmentation to further evaluate the proposed method. Using the proposed data augmentation method, accuracy of 98.53% was achieved, which is higher than the best accuracy (95.83%) obtained by the other evaluated methods of data augmentation. The paper presents the theoretical performance bound of the proposed method, and a comparison with existing papers which reveals the superiority of the proposed approach in terms of various performance metrics. The advantages of the proposed method include the elimination of the contrast agent and its complications, a lower CMR examination time, and lower costs for patients and cardiac imaging centers. © (2024) Korea Information Processing Society.

Related Docs

View other Related Docs

1. Coronary Artery Disease Detection Using Artificial Intelligence Techniques: A Survey of Trends, Geographical Differences and Diagnostic Features 1991–2020, Computers in Biology and Medicine (2021)

2. Automated Detection of Shockable Ecg Signals: A Review, Information Sciences (2021)

3. Automatic Diagnosis of Abnormal Macula in Retinal Optical Coherence Tomography Images Using Wavelet-Based Convolutional Neural Network Features and Random Forests Classifier, Journal of Biomedical Optics (2018)

4. Fh-Tabnet: Multi-Class Familial Hypercholesterolemia Detection Via a Multi-Stage Tabular Deep Learning Network, European Signal Processing Conference (2024)

5. A New Computer-Aided Diagnosis Tool Based on Deep Learning Methods for Automatic Detection of Retinal Disorders From Oct Images, International Ophthalmology (2024)

6. Deep-Covid: Predicting Covid-19 From Chest X-Ray Images Using Deep Transfer Learning, Medical Image Analysis (2020)

7. Mecardnet: A Novel Multi-Scale Convolutional Ensemble Model With Adaptive Deep Supervision for Precise Cardiac Mri Segmentation, Biomedical Signal Processing and Control (2025)

8. Retinal Optical Coherence Tomography Image Analysis by a Restricted Boltzmann Machine, Biomedical Optics Express (2022)

Experts (# of related papers)

View all Related Experts

Nizal Sarrafzadegan (4)

Saeed Kermani (3)

Style	Citing Format
MLA	Sharifrazi D, et al.. "Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques." Human-centric Computing and Information Sciences, vol. 14, no. , 2024, pp. 1-21.
APA	Sharifrazi D, Alizadehsani R, Izadi NH, Roshanzamir M, Shoeibi A, Khozeimeh F, Sani FA, Sani ZA, Hussain S, Harlapur C, Gorriz JM, Zhang YD, Khosravi A, Nahavandi S, Sarrafzadegan N, Islam SMS (2024). Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques. Human-centric Computing and Information Sciences, 14(), 1-21.
Chicago	Sharifrazi D, Alizadehsani R, Izadi NH, Roshanzamir M, Shoeibi A, Khozeimeh F, Sani FA, et al.. "Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques." Human-centric Computing and Information Sciences 14, no. (2024): 1-21.
Harvard	Sharifrazi D et al. (2024) 'Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques', Human-centric Computing and Information Sciences, 14(), pp. 1-21.
Vancouver	Sharifrazi D, Alizadehsani R, Izadi NH, Roshanzamir M, Shoeibi A, Khozeimeh F, et al.. Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques. Human-centric Computing and Information Sciences. 2024;14():1-21.
BibTex	@article{ author = {Sharifrazi D and Alizadehsani R and Izadi NH and Roshanzamir M and Shoeibi A and Khozeimeh F and Sani FA and Sani ZA and Hussain S and Harlapur C and Gorriz JM and Zhang YD and Khosravi A and Nahavandi S and Sarrafzadegan N and Islam SMS}, title = {Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques}, journal = {Human-centric Computing and Information Sciences}, volume = {14}, number = {}, pages = {1-21}, year = {2024} }
RIS	TY - JOUR AU - Sharifrazi D AU - Alizadehsani R AU - Izadi NH AU - Roshanzamir M AU - Shoeibi A AU - Khozeimeh F AU - Sani FA AU - Sani ZA AU - Hussain S AU - Harlapur C AU - Gorriz JM AU - Zhang YD AU - Khosravi A AU - Nahavandi S AU - Sarrafzadegan N AU - Islam SMS TI - Hypertrophic Cardiomyopathy Diagnosis Using Deep Learning Techniques JO - Human-centric Computing and Information Sciences VL - 14 IS - SP - 1 EP - 21 PY - 2024 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract