基于超声与细胞学图像的多模态深度学习模型预测cN0甲状腺乳头状癌风险分层
该回顾性多中心研究基于超声与细胞学图像构建多模态深度学习模型,在五个医疗中心890例接受甲状腺切除术和淋巴结清扫的PTC患者中训练与验证,并在107例测试组中评估。联合模型内部验证组AUC为0.922(0.866-0.979),测试组AUC为0.845(0.794-0.895),诊断性能超过临床模型,可准确判断N0 PTC风险分层并指导治疗决策。
要点
- 联合DL模型内部验证组AUC 0.922(0.866-0.979),测试组AUC 0.845(0.794-0.895)。
- 联合DL模型诊断性能超过临床模型。
- 图像区域热图有助于解释风险分层诊断。
核心结论
- 基于超声与细胞学图像的多模态深度学习模型能准确判断N0 PTC风险分层并指导治疗决策。
研究设计与样本
- 回顾性多中心组研究,训练与验证纳入五个医疗中心890例接受甲状腺切除术和淋巴结清扫的PTC患者,测试组为来自一个医疗中心的107例患者。
诊断标准与关键数值
- 联合DL模型内部验证组AUC 0.922(95%CI 0.866-0.979)。
- 联合DL模型测试组AUC 0.845(95%CI 0.794-0.895)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Accurately assessing the risk stratification of cN0 papillary thyroid carcinoma (PTC) preoperatively aids in making treatment decisions. We integrated preoperative ultrasound and cytological images of patients to develop and validate a multimodal deep learning (DL) model for non-invasive assessment of N0 PTC risk stratification before surgery.
METHODS: In this retrospective multicenter group study, we developed a comprehensive DL model based on ultrasound and cytological images. The model was trained and validated on 890 PTC patients undergoing thyroidectomy and lymph node dissection across five medical centers. The testing group included 107 patients from one medical center. We analyzed the model's performance, including the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.
RESULTS: The combined DL model demonstrated strong performance, with an area under the curve (AUC) of 0.922 (0.866-0.979) in the internal validation group and an AUC of 0.845 (0.794-0.895) in the testing group. The diagnostic performance of the combined DL model surpassed that of clinical models. Image region heatmaps assisted in interpreting the diagnosis of risk stratification.
CONCLUSION: The multimodal DL model based on ultrasound and cytological images can accurately determine the risk stratification of N0 PTC and guide treatment decisions.
引用
- He F, Chen S, Liu X, et al. Multimodal Deep Learning Model Based on Ultrasound and Cytological Images Predicts Risk Stratification of cN0 Papillary Thyroid Carcinoma. Acad Radiol. 2025. PMID: 40664556. doi:10.1016/j.acra.2025.06.043
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。