Milad Yousefi
1 
, Hadi Vahedi
2* , Shadi Farabi Maleki
3 , Mahya Ahmadpour Youshanlui
4 , Aida Jafari
5 , Parisa Rostami
6,7 , Kais I. Abdul-Lateef Al-Abdullah
8 , Ryszard Tadeusiewicz
9 , Paweł Pławiak
10,11 , Roohallah Alizadehsani
12 , Siamak Pedrammehr
13 1 Faculty of Mathematics, Statistics and Computer Sciences, University of Tabriz, Tabriz, Iran
2 Research Center for Evidence-Based Health Management, Maragheh University of Medical Sciences, Maragheh, Iran
3 Nikookari Eye Center, Tabriz University of Medical Sciences, Tabriz, Iran
4 Immunology Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
5 Department of Traditional Medicine, TITU University, Turkey Branch of Belgium, Van, Turkey
6 Research Center for Evidence-Based Medicine, Iranian EBM Centre: A JBI Centre of Excellence, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran
7 Student Research Committee, Tabriz university of Medical Sciences, Tabriz, Iran
8 Department of Electrical Engineering, Australian University (AU), Mubarak Al-Kabeer 1411, Kuwait
9 AGH University of Science and Technology, Department of Biocybernetics and Biomedical Engineering, Krakow, Poland
10 Department of Computer Science, Faculty of Computer Science and Telecommunications, Cracow University of Technology, Warszawska 24, 31-155 Krakow, Poland
11 Institute of Theoretical and Applied Informatics, Polish Academy of Sciences, Bałtycka 5, 44-100 Gliwice, Poland
12 Faculty of Medicine, Queensland University of Technology, Brisbane QLD Australia
13 Faculty of Design, Tabriz Islamic Art University, Tabriz, Iran
Abstract
Thyroid cancer is an increasing global health concern that requires advanced diagnostic methods. Ai-driven radiomics has shown great promise in improving diagnostic precision and predicting treatment outcomes. Therefore, this review examined the application of AI and radiomics to thyroid cancer diagnosis and treatment. Multiple databases, including PubMed, Medline, EMBASE, Scopus, and Web of Sciences, were reviewed until October 2024. A combination of keywords led to the discovery of an English academic publication on thyroid cancer and related subjects. Among the 42 investigated studies, radiomics analysis, incorporating ultrasound images, demonstrated its effectiveness in diagnosing thyroid cancer. Some studies presented new strategies that outperformed the status quo. The literature emphasized various challenges faced by AI models, including interpretability issues, dataset constraints, and operator dependence. The synthesized findings of the 42 included studies revealed the need for standardization efforts and prospective multicenter studies to address these concerns. Furthermore, several approaches to overcome these obstacles were identified, such as advances in explainable AI technology and personalized medicine techniques. Despite challenges, future research on multidisciplinary cooperation, clinical applicability validation, and algorithm improvement holds the potential to improve patient outcomes and diagnostic precision in the treatment of thyroid cancer.