多模态超声-临床融合模型预测甲状腺乳头状癌颈侧区转移
本回顾性多中心研究纳入1019例甲状腺乳头状癌患者,利用三种超声图像与15项临床变量构建多模态深度学习网络。内部测试及外部验证队列AUC分别为0.901与0.853,外部验证敏感度0.946、特异度0.652。模型可术前预测颈侧区淋巴结转移,辅助制定初始手术范围。
要点
- M-DLN对颈侧区淋巴结转移具有高敏感度0.946,有助于减少术前漏诊。
- 外部验证特异度0.652属中等水平,阳性预测受限。
- 影像与临床概率采用决策级软投票融合,便于解释与推广。
核心结论
- 融合多模态超声图像与临床数据的M-DLN可较准确术前预测甲状腺乳头状癌颈侧区淋巴结转移。
- 该模型在内部测试及外部验证队列分别取得AUC 0.901与0.853,外部验证总准确率0.874。
研究设计与样本
- 回顾性多中心研究,纳入2014—2024年两家三级中心连续1019例甲状腺乳头状癌患者。
- 训练队列710例,内部验证87例,内部测试87例,外部验证135例。
- 采用三个ResNet-50骨干提取B型、实时组织弹性成像及单色超微血流成像特征。
- 三层全连接网络处理15项临床变量,图像与临床概率经决策级软投票融合。
关键影像表现/征象
- 输入图像包括B型超声、实时组织弹性成像、单色超微血流成像。
- 模型可解释性由梯度加权类激活图与Shapley加性解释提供。
诊断标准与关键数值
- 内部测试队列M-DLN预测颈侧区淋巴结转移AUC为0.901(95%CI:0.874-0.928)。
- 外部验证队列AUC为0.853(95%CI:0.825-0.876)。
- 外部验证队列敏感度0.946,特异度0.652,总准确率0.874。
- 决策曲线分析提示M-DLN可提供实质性净临床获益。
临床应用与阅片要点
- 对颈侧区淋巴结转移的高敏感度有助于减少术前漏诊与避免治疗不足。
- 中等特异度可能导致一定假阳性,报告时需结合常规超声征象综合判断。
- 该系统为开源模型,可利用常规采集的多模态超声图像与临床数据术前评估。
局限性
- 特异度仅0.652,假阳性风险不可忽略。
- 来源为回顾性研究,两中心数据构建,缺少前瞻性验证。
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
OBJECTIVE: Lateral cervical lymph node metastasis (LLNM) is missed in up to 30% of papillary thyroid carcinoma (PTC) patients pre-operatively, leading to incomplete surgery or unnecessary two-stage lateral neck dissection. Here we aimed to develop and externally validate a multimodal deep learning network (M-DLN) that fuses ultrasound images with clinical factors for the pre-operative prediction of LLNM.
METHODS: In this retrospective, multicentre study, 1019 consecutive PTC patients (2014-2024) from two tertiary centres were split into training (n = 710), internal validation (n = 87), internal test (n = 87) and external validation (n = 135) cohorts. Three ResNet-50 backbones extracted features from type B, real-time tissue elastography and monochrome superb microvascular imaging ultrasound; a three-layer, fully connected network processed 15 clinical variables. Decision-level soft-voting fused image and clinical probabilities. Model explainability was provided by gradient-weighted class activation mapping and Shapley additive explanations. Discrimination, calibration and clinical utility were assessed by area under the curve and decision curve analysis.
RESULTS: In both the internal test cohort and external validation cohort, the M-DLN model-comprising a deep learning network based on multimodal ultrasound images integrated with clinical information-demonstrated a highly efficient and robust performance in predicting LLNM in PTC, with areas under the curve of 0.901 (95% confidence interval: 0.874-0.928) and 0.853 (95% confidence interval: 0.825-0.876), respectively. Decision curve analysis indicated that M-DLN provided a substantial net clinical benefit. In the external validation cohort, our M-DLN model yielded a high sensitivity of 0.946, a moderate specificity of 0.652 and an overall accuracy of 0.874. The high sensitivity effectively reduced the rate of missed LLNM diagnosis, which is essential to avoid under-treatment, while the moderate specificity was acceptable given the clinical priorities.
CONCLUSION: The open-source M-DLN system, integrating routinely acquired multimodal ultrasound images with clinical data, provides accurate, interpretable and externally validated pre-operative identification of LLNM in PTC, and could guide initial thyroid surgery precision.
引用
- Wu, Kuang, Zhu, et al. Multimodal Deep Fusion of Ultrasound Images and Clinical Factors for Pre-operative Prediction of Lateral Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma. Ultrasound Med Biol. 2026. PMID: 42469052. doi:10.1016/j.ultrasmedbio.2026.06.017
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。