year 13, Issue 1 (5-2026)
CJS 2026, 13(1): 12-25 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Sayyahi A, Alavi S E, Jaderian M. A Scientometric Study of Machine Learning and Deep Learning Methods for Non-Alcoholic Fatty Liver Disease Detection in Medical Imaging. CJS 2026; 13 (1) :12-25
URL: http://cjs.mubabol.ac.ir/article-1-411-en.html
URL: http://cjs.mubabol.ac.ir/article-1-411-en.html
Department of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran , Se.Alavi@scu.ac.ir
Abstract: (357 Views)
Background and aim: This study aims to map the landscape of research related to the detection of non-alcoholic fatty liver disease (NAFLD) using various medical imaging techniques, including ultrasound, MRI, and CT scan, through machine learning and deep learning.
Materials and methods: The scientometric analysis for scientific publications indexed in databases like WoSCC, IEEE Xplore, Scopus and PubMed was done in this descriptive study. The combination of keywords was utilized to identify articles on machine learning, deep learning, and NAFLD detection in medical imaging. The focus in this analysis was on identifying publication trends, geographic distribution, and major sources of research.
Findings: The findings indicated a remarkable increase in the use of machine learning and deep learning techniques for NAFLD detection, especially in the last decade. The United States, China, and India emerged as the biggest contributors in this field. Another interesting finding is related to the importance of international collaboration for the advancement of this field. The collaboration between top universities and international research groups played a very important role in the advancement of research in this field.
Conclusion: According to this scientometric analysis, artificial intelligence is revolutionizing NAFLD diagnosis. Although recent research has reached a noteworthy diagnostic accuracy, especially regarding deep learning, the real-world clinical impact is limited by factors beyond just numerical performance. Research is now shifting focus from mere accuracy to developing interpretable, trustworthy, and clinically applicable models. These results indicate that future AI-driven diagnosis of NAFLD must align technological innovation with practical clinical needs to achieve faster and fairer diagnoses.
Materials and methods: The scientometric analysis for scientific publications indexed in databases like WoSCC, IEEE Xplore, Scopus and PubMed was done in this descriptive study. The combination of keywords was utilized to identify articles on machine learning, deep learning, and NAFLD detection in medical imaging. The focus in this analysis was on identifying publication trends, geographic distribution, and major sources of research.
Findings: The findings indicated a remarkable increase in the use of machine learning and deep learning techniques for NAFLD detection, especially in the last decade. The United States, China, and India emerged as the biggest contributors in this field. Another interesting finding is related to the importance of international collaboration for the advancement of this field. The collaboration between top universities and international research groups played a very important role in the advancement of research in this field.
Conclusion: According to this scientometric analysis, artificial intelligence is revolutionizing NAFLD diagnosis. Although recent research has reached a noteworthy diagnostic accuracy, especially regarding deep learning, the real-world clinical impact is limited by factors beyond just numerical performance. Research is now shifting focus from mere accuracy to developing interpretable, trustworthy, and clinically applicable models. These results indicate that future AI-driven diagnosis of NAFLD must align technological innovation with practical clinical needs to achieve faster and fairer diagnoses.
Keywords: Machine Learning (ML), Deep Learning (DL), Non-Alcoholic Fatty Liver Disease (NAFLD), Medical imaging
Type of Study: Orginal |
Subject:
Scientometrics
Received: 2025/11/6 | Revised: 2026/03/12 | Accepted: 2026/03/30 | ePublished: 2026/04/15
Received: 2025/11/6 | Revised: 2026/03/12 | Accepted: 2026/03/30 | ePublished: 2026/04/15
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
