The thyroid imaging reporting and data system (TIRADS) was developed as a standard global term to describe thyroid nodule risk features, aiming to address issues such as variability and low reproducibility in nodule feature detection and interpretation by different physicians. The objective of this study is to comprehensively study articles that utilize AI techniques to design and develop decision support systems for classifying thyroid nodule risk on the basis of various TIRADS guidelines from ultrasound images. This protocol includes five steps: identification of key research questions of the review, descriptions of the systematic literature search strategies, criteria for study inclusion and exclusion, study quality measures, and the data extraction process. We designed a complete search string using PubMed, Scopus, and Web of Sciences to retrieve all relevant English language studies up to January 2024. A PRISMA diagram was constructed, inclusion and exclusion criteria were defined, and after a quality assessment of the included papers, relevant data were extracted. The protocol of this systematic review was registered in the PROSPERO database (CRD42024551311). We anticipate that our findings will assist researchers in creating higher-quality systems with increased efficiency, reducing unnecessary biopsies, improving the reproducibility and reliability of thyroid nodule diagnostics, and providing good educational opportunities for less experienced physicians. In this study, a protocol was used for performing a systematic review to evaluate the diagnostic performance and other various aspects used in the design and development of artificial intelligence CAD systems based on various thyroid imaging reporting and data systems (TI-RADSs).
Read full abstract