Intelligent diagnosis of thyroid nodules with AI ultrasound assistance and cytology classification

作者：Cai Xu, Yifeng Zhou, Jie Ren, Jinrong Wei, Shiyu Lu, Huaimin GU, Weihong Xu, Xun Zhu · 发表于：Frontiers in Endocrinology · 年份：2025 · DOI：10.3389/fendo.2025.1546983 · 被引用次数：13 · 研究领域：Thyroid Cancer Diagnosis and Treatment、AI in cancer detection、Artificial Intelligence in Healthcare and Education

Objective: Accurate evaluation of thyroid nodules is crucial for effective management; however, methods such as ultrasonography and Fine Needle Aspiration Cytology (FNAC) can be subjective and operator-dependent. Indeterminate thyroid nodules (ITNs) complicate diagnosis, coming at the expense of time, money, and potentially additional FNA samplings, causing more discomfort for the patients. Recent advancements in artificial intelligence (AI) assisted ultrasound diagnosis system have demonstrated excellent diagnostic performance and the potential to aid in the differentiation of ITNs. This study aims to develop an AI classifier that integrates the AI-assisted ultrasound diagnosis system, FNAC, and demographic data to enhance the differentiation of benign and malignant thyroid nodules, and to compare the diagnostic performance of the models, with a focus on diagnosing ITNs. Materials and methods: In the present research, 620 thyroid nodules were collected from a single medical center and divided into training and testing cohorts (Testing1). We developed five AI models using distinct classification algorithms (Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine) that integrate demographic data, cytological findings, and an AI-assisted ultrasound diagnostic system for thyroid nodule assessment. These models underwent prospective validation (Testing2, n = 243) to identify the optimal model. A subsequent prospective study (T...