BackMix-Enhanced Semi-Supervised Learning for Automated Detection of Aortic Stenosis from Transthoracic Echocardiographic Images

Fatima Ezzahra  Elkouahy; Badreddine Labakoum; Hajar  Ouahid; Mansoor  Alam; Hamid  El Malali; Lhoucine  Ben Taleb; Azeddine  Mouhsen

doi:10.35882/jeeemi.v8i3.1657

Fatima Ezzahra Elkouahy Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco https://orcid.org/0009-0006-6398-1231
Badreddine Labakoum Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco. https://orcid.org/0009-0004-6414-3614
Hajar Ouahid Bioscience, and Health Research Laboratory, Faculty of Medicine and Pharmacy, Cadi Ayyad University, Marrakech, Morocco https://orcid.org/0000-0002-1098-3827
Mansoor Alam University of Engineering and Technology, Peshawar, Pakistan https://orcid.org/0000-0003-1732-205X
Hamid El Malali Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco https://orcid.org/0000-0002-5624-3816
Lhoucine Ben Taleb Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco https://orcid.org/0000-0002-0926-2694
Azeddine Mouhsen Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco https://orcid.org/0000-0003-3901-4736

DOI: https://doi.org/10.35882/jeeemi.v8i3.1657

Keywords: Aortic stenosis, Transthoracic echocardiography, Semi-supervised learning, Anatomically guided BackMix, Shortcut learning, Deep learning

Abstract

Aortic stenosis (AS) is a prevalent and progressive valvular heart disease requiring accurate severity assessment for optimal clinical decision-making. Transthoracic echocardiography (TTE) is the standard diagnostic modality; however, its interpretation remains operator-dependent and subject to inter-observer variability. In this study, we propose an anatomically guided BackMix-enhanced semi-supervised learning framework for automated echocardiographic view classification and AS severity assessment. The approach leverages Gradient-weighted Class Activation Mapping (Grad-CAM) to preserve diagnostically relevant anatomical regions during augmentation while modifying background areas to mitigate shortcut learning. A semi-supervised self-training strategy combined with an ensemble classification framework was used to exploit both labeled and unlabeled data. The framework was evaluated on the TMED2 dataset of echocardiography, comprising 24,964 TTE images. To assess generalizability, external validation was performed on an independent dataset of 300 cardiologist-labeled echocardiographic images, including apical four-chamber (A4C), parasternal long-axis (PLAX), and parasternal short-axis (PSAX) views. Experimental results demonstrated that the proposed method outperformed the baseline semi-supervised model, improving view classification accuracy by approximately 3% and AS severity classification accuracy by 4–6%, with the largest gain observed in moderate AS. Performance remained consistent on the external validation dataset, supporting the robustness of the proposed approach. Statistical analysis confirmed the significance of these improvements (p < 0.01). Grad-CAM evaluation further demonstrated improved localization of clinically relevant regions. These findings suggest that anatomically guided BackMix augmentation combined with semi-supervised ensemble learning can improve classification accuracy, robustness, and interpretability in echocardiographic analysis under limited annotation conditions, offering a promising approach for automated AS assessment across independent clinical datasets

Downloads

Download data is not yet available.

Author Biographies

Fatima Ezzahra Elkouahy, Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco

FATIMA EZZAHRA ELKOUAHY was born on August 6, 1996, in Morocco. She is a biomedical engineer and Ph.D. researcher specializing in cardiovascular imaging and artificial intelligence applications in echocardiography. She received her master’s degree in biomedical engineering and is currently pursuing her doctoral research focusing on automated analysis of echocardiographic data for the detection and evaluation of valvular heart diseases, particularly aortic stenosis. Her research interests include medical imaging, artificial intelligence in healthcare, ultrasound technologies, and biomedical instrumentation. She works at the Faculty of Sciences and Techniques, Hassan 1st University, Settat, Morocco. She can be contacted at elkouahyfat.fst@uhp.ac.ma

Badreddine Labakoum, Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco.

LABAKOUM BADREDDINE was born on October 22, 1994, in Agadir, Morocco. He is a Ph.D. student and received his master’s degree in biomedical engineering: instrumentation and maintenance from the Faculty of Science and Technology Settat in 2017. His research areas include the applications and evaluation of 3D printing in the medical field and biomedical instrumentation. He works at the Laboratory of Energy-Materials-Instrumentation and Telecom (EMIT), Faculty of Sciences and Technology, Hassan 1st University, Morocco. BP: 577, road to Casablanca. Settat, Morocco. He can be contacted at b.labakoum@uhp.ac.ma

Hajar Ouahid, Bioscience, and Health Research Laboratory, Faculty of Medicine and Pharmacy, Cadi Ayyad University, Marrakech, Morocco

HAJAR OUAHID is the Head of the Healthcare Workforce Planning and Utilization Office at Ibn Tofail Hospital, Mohammed VI University Hospital, Marrakech, Morocco. She holds a Master’s degree in Public Health and Hospital Management and a PhD in Epidemiology and Public Health from Cadi Ayyad University, affiliated with the Bioscience and Health Research Laboratory, Marrakech, Morocco. Her academic and professional interests focus on public health, epidemiology, and healthcare management. She can be contacted at ouahid.hajar.1@gmail.com

Mansoor Alam, University of Engineering and Technology, Peshawar, Pakistan

MANSOOR ALAM was born on July 21, 1994, in Pakistan. He is a Senior AI/ML Engineer and Robotics Specialist with more than six years of experience in developing advanced artificial intelligence solutions. He received his MS degree in Mechatronics Engineering from the University of Engineering and Technology (UET) Peshawar in 2021, after completing his BS in Mechatronics Engineering from the same university in 2016. His research and professional work focus on artificial intelligence, computer vision, robotics, autonomous systems, and medical image analysis. He has developed AI solutions for cancer detection, autonomous mobile robots, drone detection and tracking, and precision agriculture systems. Currently, he works as an Assistant Manager AI/ML at NSTP Islamabad, where he leads the development of AI-based solutions. He can be contacted at mansooralam129047@gmail.com

Hamid El Malali, Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco

Hamid El Malali was born in Errich- Midelt, Morocco. He holds a doctorate in Biomedical Engineering and Instrumentation Laboratory “RMI” in the Science and Technology Faculty, Hassan 1st University, Settat, Morocco. He holds a bachelor’s in physics from Sidi Mohammed ben Abdellah University, Fes in 1997, and a Master of Science and Technology in Biomedical Engineering and Instrumentation from Hassan 1st University, Settat in 2016. His research interests are computer vision, image processing, machine learning, and artificial intelligence. In 2003, he holds a diploma in computer science from the Regional Pedagogical Center of Fez. Currently, he is a professor of physics and medical imaging at Hassan First University, Settat Morocco. He can be contacted at email: h.elmalali@uhp.ac.ma.

Lhoucine Ben Taleb, Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco

Lhoucine Ben Taleb was born on February 20, 1991. He received his Ph.D. degree in Biomedical Engineering in 2020. He is currently a Professor of Biomedical Engineering at Hassan First University, Morocco, and a member of the Energy–Matter–Instrumentation & Telecommunications Laboratory. His teaching activities focus on biomedical instrumentation and medical imaging technologies.

His research interests include the design and development of biomedical instrumentation systems, medical signal acquisition and processing, artificial intelligence applied to healthcare systems, and advanced medical imaging techniques. He has been involved in academic training and supervision of engineering students, contributing to the development of practical and research-oriented skills in the field of biomedical engineering. He can be contacted at l.bentaleb@uhp.ac.ma

Azeddine Mouhsen , Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco

Azeddine Mouhsen was born on July 10, 1967 and is now a professor of Physics at Hassan First University, Morocco, since 1996. He holds a Ph.D. from Bordeaux I University (France) in 1995 and a thesis from Moulay Ismail University, Morocco, in 2001. He specializes in instrumentation and measurements, sensors, applied optics, energy transfer, and radiation-matter interactions. Azeddine Mouhsen has taught courses in physical sensors, chemical sensors, instrumentation, systems technology, digital electronics, and industrial data processing. He has published over 45 papers, and he is the co-inventor of one patent. He is the Director of the Laboratory of Energy-Materials-Instrumentation and Telecom (EMIT). He can be contacted at az.mouhsen@gmail.com

References

C. M. Otto and B. Prendergast, “Aortic-Valve Stenosis — From Patients at Risk to Severe Valve Obstruction,” New England Journal of Medicine, vol. 371, no. 8, pp. 744–756, Aug. 2014, doi: 10.1056/nejmra1313875.

P. Guedeney and J. P. Collet, “Aortic stenosis: An update,” Mar. 2022, doi: 10.1016/j.revmed.2021.06.003.

B. R. Lindman et al., “Calcific aortic stenosis,” Nat. Rev. Dis. Primers, vol. 2, Mar. 2016, doi: 10.1038/nrdp.2016.6.

E. M. Isselbacher et al., “2022 ACC/AHA Guideline for the Diagnosis and Management of Aortic Disease: A Report of the American Heart Association/American College of Cardiology Joint Committee on Clinical Practice Guidelines,” J. Am. Coll. Cardiol., vol. 80, no. 24, pp. e223–e393, Dec. 2022, doi: 10.1016/j.jacc.2022.08.004.

H. Krishna et al., “Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography,” Journal of the American Society of Echocardiography, vol. 36, no. 7, pp. 769–777, Jul. 2023, doi: 10.1016/j.echo.2023.03.008.

R. Manzo et al., “Echocardiographic Evaluation of Aortic Stenosis: A Comprehensive Review,” Aug. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/diagnostics13152527.

W. A. Zoghbi et al., “Recommendations for Evaluation of Prosthetic Valves With Echocardiography and Doppler Ultrasound. A Report from the American Society of Echocardiography’s Guidelines and Standards Committee and the Task Force on Prosthetic Valves, Developed in Conjunction With the American College of Cardiology Cardiovascular Imaging Committee, Cardiac Imaging Committee of the American Heart Association,” Journal of the American Society of Echocardiography, vol. 22, no. 9, pp. 975–1014, Sep. 2009, doi: 10.1016/j.echo.2009.07.013.

Y. Saijo et al., “Software Variability in Measurement of LV Mechanical Dispersion in Patients With LV Hypertrophy,” Apr. 01, 2020, Elsevier Inc. doi: 10.1016/j.jcmg.2019.10.009.

K. V. Bunting, R. P. Steeds, K. Slater, J. K. Rogers, G. V. Gkoutos, and D. Kotecha, “A Practical Guide to Assess the Reproducibility of Echocardiographic Measurements,” Dec. 01, 2019, Elsevier Inc. doi: 10.1016/j.echo.2019.08.015.

A. C. Armstrong et al., “Quality Control and Reproducibility in M-Mode, Two-Dimensional, and Speckle Tracking Echocardiography Acquisition and Analysis: The CARDIA Study, Year 25 Examination Experience,” Echocardiography, vol. 32, no. 8, pp. 1233–1240, Aug. 2015, doi: 10.1111/echo.12832.

Y. Muhammad, M. Tahir, M. Hayat, and K. T. Chong, “Early and accurate detection and diagnosis of heart disease using intelligent computational model,” Sci. Rep., vol. 10, no. 1, Dec. 2020, doi: 10.1038/s41598-020-76635-9.

A. Narang, R. Bae, H. Hong, Y. Thomas, S. Surette, A. Cadieu, et al., “Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use,” JAMA Cardiology, vol. 6, no. 6, pp. 624–632, Jun. 2021, doi: 10.1001/jamacardio.2021.0185.

R. Geirhos et al., “Shortcut learning in deep neural networks,” Nat. Mach. Intell., vol. 2, no. 11, pp. 665–673, Nov. 2020, doi: 10.1038/s42256-020-00257-z.

A. Madani, J. R. Ong, A. Tibrewal, and M. R. K. Mofrad, “Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease,” NPJ Digit. Med., vol. 1, no. 1, Dec. 2018, doi: 10.1038/s41746-018-0065-x.

G. Holste et al., “Severe aortic stenosis detection by deep learning applied to echocardiography,” Eur. Heart J., vol. 44, no. 43, pp. 4592–4604, Nov. 2023, doi: 10.1093/eurheartj/ehad456.

A. Ulloa, L. Jing, C. W. Good, D. P. van Maanen, S. Raghunath, J. D. Suever, et al., “A Deep Neural Network Predicts Survival After Heart Imaging Better Than Cardiologists,” arXiv preprint arXiv:1811.10553, 2018, doi: 10.48550/arXiv.1811.10553.

A. Mahesh, D. Banerjee, A. Saha, M. R. Prusty, and A. Balasundaram, “CE-EEN-B0: Contour Extraction Based Extended EfficientNet-B0 for Brain Tumor Classification Using MRI Images,” Computers, Materials and Continua, vol. 74, no. 3, pp. 5967–5982, 2023, doi: 10.32604/cmc.2023.033920.

O. Hamila, S. Ramanna, C. J. Henry, S. Kiranyaz, R. Hamila, R. Mazhar, and T. Hamid, “Fully Automated 2D and 3D Convolutional Neural Networks Pipeline for Video Segmentation and Myocardial Infarction Detection in Echocardiography,” Multimedia Tools and Applications, vol. 81, no. 26, pp. 37417–37439, Nov. 2022, doi: 10.1007/s11042-021-11579-4.

Danielsen R, Nordrehaug JE, Stangeland L, Vik-Mo H. Limitations in assessing the severity of aortic stenosis by Doppler gradients. Br Heart J. 1988;59(5):551-555. doi:10.1136/hrt.59.5.551.

Chen C, Han J, Debattista K. Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels. IEEE Trans Pattern Anal Mach Intell. 2024;46(8):5595-5611. doi:10.1109/TPAMI.2024.3367416

Bransby KM, Beqiri A, Cho Kim WJ, Oliveira J, Chartsias A, Gomez A. BackMix: mitigating shortcut learning in echocardiography with minimal supervision. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. Lecture Notes in Computer Science. Cham: Springer Nature Switzerland; 2024. p. 570–579. doi:10.1007/978-3-031-72083-3_53.

A. Hayek et al., “Impact of Arterial Blood Pressure on Ultrasound Hemodynamic Assessment of Aortic Valve Stenosis Severity,” Journal of the American Society of Echocardiography, vol. 33, no. 11, pp. 1324–1333, Nov. 2020, doi: 10.1016/j.echo.2020.06.013.

Wang Y, Mu J, Huang H, Wang Q, Zhu P, Hu Q. BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors. IEEE Trans. Pattern Anal. Mach. Intell. 2025;47(8):6172–6183. doi: 10.1109/TPAMI.2025.3550703.

X. Zhou and M. Belkin, “Semi-Supervised Learning,” in Academic Press Library in Signal Processing, vol. 1, P. S. R. Diniz, J. A. K. Suykens, R. Chellappa, and S. Theodoridis, Eds. Waltham, MA: Elsevier, 2014, pp. 1239–1269, doi: 10.1016/B978-0-12-396502-8.00022-X.

Z. Huang, G. Long, B. S. Wessler, and M. C. Hughes, “TMED-2: A Dataset for Semi-Supervised Classification of Echocardiograms,” in DataPerf: Benchmarking Data for Data-Centric AI Workshop at ICML, 2022. doi: 10.48550/arXiv.2108.00080.

F. Ezzahra Elkouahy, A. Bennis, N. Merke, H. Ouahid, H. El Malali, L. Ben Taleb, and A. Mouhsen, “Advanced Diagnosis of Aortic Stenosis Disease Based on Ultrasound Images: A Novel Artificial Intelligence Approach,” Advanced Ultrasound in Diagnosis and Therapy, vol. 9, no. 3, pp. 298–306, 2025, doi: 10.26599/AUDT.2025.240067.

S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, “CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 6023–6032, doi: 10.1109/ICCV.2019.00612.

P. R. A. S. Bassi, S. S. J. Dertkigil, and A. Cavalli, “Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization,” Nature Communications, vol. 15, no. 1, Art. no. 291, Jan. 2024, doi: 10.1038/s41467-023-44371-z

P. Overtchouk et al., “Long-Term Mortality and Early Valve Dysfunction According to Anticoagulation Use: The FRANCE TAVI Registry,” J. Am. Coll. Cardiol., vol. 73, no. 1, pp. 13–21, Jan. 2019, doi: 10.1016/j.jacc.2018.08.1045.

T. M. Morrison, N. Pathak, J. Haynes, et al., “EchoNet-Dynamic: a large new cardiac motion video data resource for medical machine learning,” Circulation, vol. 142, no. 16, pp. 1401–1412, 2020, doi: 10.1161/CIRCULATIONAHA.120.046916.

Y. Zhu et al., “Automatic view classification of contrast and non-contrast echocardiography,” Front. Cardiovasc. Med., vol. 9, Sep. 2022, doi: 10.3389/fcvm.2022.989091.

Z. Huang, B. S. Wessler, and M. C. Hughes, “Detecting heart disease from multi-view ultrasound images via supervised attention multiple instance learning,” in Proceedings of the 8th Machine Learning for Healthcare Conference, PMLR 219, 2023, pp. 285–307, doi: 10.48550/arXiv.2306.00003.

A. Hagendorff et al., “Expert consensus document on the assessment of the severity of aortic valve stenosis by echocardiography to provide diagnostic conclusiveness by standardized verifiable documentation,” Mar. 2020, doi: 10.1007/s00392-019-01539-2

O. Bernard et al., “Standardized Evaluation System for Left Ventricular Segmentation Algorithms in 3D Echocardiography,” IEEE Trans. Med. Imaging, vol. 35, no. 4, pp. 967–977, Apr. 2016, doi: 10.1109/TMI.2015.2503890

O. Chapelle, B. Schölkopf, and A. Zien, Semi-supervised learning. Cambridge (MA): MIT Press, 2006, doi: 10.7551/mitpress/9780262033589.001.0001.

D. H. Lee, “Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks,” arXiv preprint arXiv:1307.1770, 2013, doi: 10.48550/arXiv.1307.1770.

H. Chen, X. Li, H. Qiao, A. Chen, and K. Cai, “A decision tree network with semi-supervised entropy learning strategy for spectroscopy aided detection of blood hemoglobin,” Spectrochim. Acta Part A Mol. Biomol. Spectrosc., vol. 291, p. 122354, Apr. 2023, doi: 10.1016/j.saa.2023.122354.

A. Tarvainen and H. Valpola, “Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, doi: 10.48550/arXiv.1703.01780.

S. Suara, A. Jha, P. Sinha, and A. A. Sekh, “Is Grad-CAM Explainable in Medical Images”, Jul. 2023, doi: 10.1007/978-3-031-58181-6_11.

G. Holste, E. K. Oikonomou, B. J. Mortazavi, Z. Wang, and R. Khera, “Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning,” Commun. Med., vol. 4, no. 1, Dec. 2024, doi: 10.1038/s43856-024-00538-3.

C. R. Johnson, S. de Vries, K. Wohlgemuth, and S. Lucia, “Multi-stage model predictive control for slug flow crystallizers using uncertainty-aware surrogate models,” Oct. 2025, doi: 10.1016/j.compchemeng.2025.109456.

D. Sun, F. Dornaika, and N. Barrena, “HSMix: Hard and soft mixing data augmentation for medical image segmentation,” Information Fusion, vol. 115, Mar. 2025, doi: 10.1016/j.inffus.2024.102741.

D. X. Augustine et al., “Echocardiographic assessment of pulmonary hypertension: A guideline protocol from the British Society of Echocardiography,” Echo Res. Pract., vol. 5, no. 3, pp. G11–G24, Sep. 2018, doi: 10.1530/ERP-17-0071.

E. Hagberg et al., “Semi-supervised learning with natural language processing for right ventricle classification in echocardiography—a scalable approach,” Comput. Biol. Med., vol. 143, Apr. 2022, doi: 10.1016/j.compbiomed.2022.105282.

T. Mori, T. Watanabe, and S. Kosugi, “Exploring ethical considerations in medical research: Harnessing pre-generated transformers for AI-powered ethics discussions,” PLoS One, vol. 20, no. 2, Feb. 2025, doi: 10.1371/journal.pone.0311148.

C. Oprea et al., “Evaluating the Explainable AI Method Grad-CAM for Breath Classification on Newborn Time Series Data,” in IFAC-PapersOnLine, Elsevier B.V., Sep. 2024, pp. 123–128, doi: 10.1016/j.ifacol.2024.11.023.

M. Skliarov, R. El Shawi, C. Dhaoui, and N. Ahmed, “A comparative evaluation of explainability techniques for image data,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-25839-y

D. Ouyang et al., “Video-based AI for beat-to-beat assessment of cardiac function,” Nature, vol. 580, no. 7802, pp. 252–256, Apr. 2020, doi: 10.1038/s41586-020-2145-8.

T. Tohyama et al., “Multi-View Echocardiographic Embedding for Accessible AI Development,” Aug. 19, 2025, doi: 10.1101/2025.08.15.25333725.

P. L. Myhre et al., “Artificial intelligence-enhanced echocardiography in cardiovascular disease management,” Mar. 2025, doi: 10.1038/s41569-025-01197-0.

A. Correa, A. A. Joshi, and E. Argulian, “Three-Dimensional Echocardiographic Evaluation of Indentations of the Posterior Mitral Leaflet and Their Impact on Secondary Mitral Regurgitation,” J. Am. Soc. Echocardiogr., vol. 36, no. 1, pp. 114–116, Jan. 2023, doi: 10.1016/j.echo.2022.08.002.

S. Leclerc, E. Smistad, J. Pedrosa, A. Østvik, F. Cervenansky, F. Espinosa, et al., “Deep learning for segmentation using an open large-scale dataset in 2D echocardiography,” IEEE Trans. Med. Imaging, vol. 38, no. 9, pp. 2198–2210, 2019, doi: 10.1109/TMI.2019.2900516.

M. Alsharqi, W. J. Woodward, J. A. Mumith, D. C. Markham, R. Upton, and P. Leeson, “Artificial intelligence and echocardiography,” Echo Res. Pract., vol. 5, no. 4, pp. R115–R126, 2018, doi: 10.1530/ERP-18-0056.

Y. E. Yoon, S. Kim, and H. J. Chang, “Artificial Intelligence and Echocardiography,” Journal of Cardiovascular Imaging, vol. 29, no. 3, pp. 193–204, Jul. 2021, doi: 10.4250/jcvi.2021.0039.

W. Chen, Y. Xie, Z. Zhang, Y. Zhu, Y. Zhang, S. Zhu, C. Wu, Z. Zhang, X. Yang, M. Liu, X. Xie, and M. Zhang, “Artificial intelligence-assisted medical imaging in interventional management of valvular heart disease,” Adv. Ultrasound Diagn. Ther., vol. 7, no. 3, pp. 217–227, 2023, doi: 10.37015/AUDT.2023.230030.

M. Donato, N. Ferri, M. G. Lupo, E. Faggin, and M. Rattazzi, “Current evidence and future perspectives on pharmacological treatment of calcific aortic valve stenosis,” Nov. 2020, doi: 10.3390/ijms21218263.

R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, and N. Elhadad, “Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission,” in Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., Aug. 2015, pp. 1721–1730, doi: 10.1145/2783258.2788613.