Improved diagnosis of thyroid cancer aided with deep learning applied to sonographic text reports: a retrospective, multi-cohort, diagnostic study.

Qiang ZhangSheng ZhangJianxin LiYi PanJing ZhaoYixing FengYanhui ZhaoXiaoqing WangZhiming ZhengXiangming YangLixia LiuChunxin QinKe ZhaoXiaonan LiuCaixia LiLiuyang ZhangChunrui YangNa ZhuoHong ZhangJie LiuJinglei GaoXiaoling DiFanbo MengWei JiMeng YangXiaojie XinXi WeiRui JinLun ZhangXudong WangFengju SongXiangqian ZhengMing GaoKexin ChenXiangChun Li

Published in: Cancer biology & medicine (2021)

THCaDxNLP achieved a high AUROC for the identification of thyroid cancer, and improved the accuracy, sensitivity, and precision of thyroid ultrasound radiologists. This warrants further investigation of THCaDxNLP in prospective clinical trials.

Keyphrases

deep learning
clinical trial
artificial intelligence
magnetic resonance imaging
smoking cessation
ultrasound guided
computed tomography
optic nerve