AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant

• DOI: 10.48550/arxiv.2402.02401
• Publication Date: 2024-02-04
• Authors: Jincao Yao; Yunpeng Wang; Zhikai Lei; Kai Wang; Xiaoxian Li; Jianhua Zhou; Xiang Hao; Jiafei Shen; Zhenping Wang; Rongrong Ru; Yaqing Chen; Yahan Zhou; Chen Chen; Yanming Zhang; Ping Liang; Dong Xu
• Keywords: Thyroid Nodules; Content (measure theory)

An artificial intelligence-generated content-enhanced computer-aided diagnosis (AIGC-CAD) model, designated as ThyGPT, has been developed. This inspired by the architecture of ChatGPT, could assist radiologists in assessing risk thyroid nodules through semantic-level human-machine interaction. A dataset comprising 19,165 nodule ultrasound cases from Zhejiang Cancer Hospital was assembled to facilitate training and validation model. After training, ThyGPT automatically evaluate engage effective communication with physicians human-computer The performance rigorously quantified using established metrics such receiver operating characteristic (ROC) curve, area under curve (AUC), sensitivity, specificity. empirical findings revealed that radiologists, when supplemented markedly surpassed diagnostic acumen their peers utilizing traditional methods well model isolation. These suggest AIGC-CAD systems, exemplified hold promise fundamentally transform workflows forthcoming years.