摘要
目的:探讨甲状腺结节AI超声辅助诊断系统在住院医师规范化培训教学中的应用效果。方法:选取2019年1月至2019年12月在广东省第二人民医院行甲状腺手术及超声检查的108名患者,共155个甲状腺结节,由两位2年级超声专业住院医师采用2017年美国放射学会发布的甲状腺影像报告与数据系统甲状腺结节超声指南(ACR TI-RADS)评估甲状腺结节;之后两位住院医师联合基于ACR TI-RADS超声特征的AI超声辅助诊断系统的预测结果再次评估上述结节。诊断标准以甲状腺结节手术病理结果作为金标准。结果:通过AI超声辅助诊断系统后,两位住院医师诊断甲状腺结节的AUC均有所提高。另外,两位住院医师联合AI超声辅助诊断系统在识别甲状腺结节的点状强回声方面的能力均得到提高,其中一位医师在识别甲状腺结构、回声、形状、分叶或不规则方面也有所提高。结论:与传统教学模式相比,应用甲状腺结节的AI超声辅助诊断系统可以帮助住院医师在较短的时间内提高掌握ACR TI-RADS指南的熟悉度,提高对结节超声特征的识别能力,缩短培训周期,起到辅助临床教学培训的作用。
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.
作者
崔楠
陈雨凡
柏通
马力
刘红梅
CUI Nan;CHEN Yufan;BAI Tong;MA Li;LIU Hongmei(Department of Ultrasound/Institute of Ultrasound in Musculoskeletal Sports Medicine,Guangdong Second Provincial General Hospital,Guangzhou 510317,China;The Second Clinical Medical College,Southern Medical University,Guangzhou 510317,China)
出处
《中国医学物理学杂志》
CSCD
2023年第10期1233-1236,共4页
Chinese Journal of Medical Physics
基金
广东省医学科研基金(A2023043)。
关键词
人工智能
甲状腺结节
超声医学
住院医师规范化培训
教学
artificial intelligence
thyroid nodule
ultrasonic medicine
standardized training for resident doctor
teaching