Abstract

Info

Title:: Application of ACR TI-RADS-based computer-aided diagnosis system for thyroid nodules in the teaching practice of standardized training for resident doctors

Author(s):: CUI Nan1; CHEN Yufan2; BAI Tong1; MA Li1; LIU Hongmei1; 1. Department of Ultrasound/Institute of Ultrasound in Musculoskeletal Sports Medicine, Guangdong Second Provincial General Hospital, Guangzhou 510317, China 2. The Second Clinical Medical College, Southern Medical University, Guangzhou 510317, China

Keywords:: Keywords: artificial intelligence thyroid nodule ultrasonic medicine standardized training for resident doctor teaching

Abstract:: Abstract: Objective To explore the role of ACR TI-RADS-based computer-aided diagnosis system (MTIRADS) for thyroid nodules in the teaching practice of standardized resident training. Methods A total of 155 thyroid nodules which underwent thyroid surgery and ultrasonic examination from January to December 2019 were evaluated by two residents using 2017 American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS). Then, the two residents referred to the prediction results of MTIRADS based on the ultrasonic features of ACR TI-RADS and revaluated the above nodules. The surgical and pathological findings of thyroid nodules were taken as the golden standard. Results After using MTIRADS for thyroid nodule diagnosis, the two residents achieved a higher AUC. In addition, the ability of the two residents to recognize the dotted high-echoes in thyroid nodules was improved after referring to MTIRADS results, and one of the residents improved the accuracy in identifying thyroid structure, echo, shape, lobulation or irregularity. Conclusion Compared with the traditional teaching mode, MTIRADS can help residents to increase their familiarity with ACR TI-RADS, improve their ability to recognize the ultrasonic features of nodules, shorten training cycle. MTIRADS could become an effective way in assisting clinical teaching and training.