文献速递甲状腺与浅表头颈技术与安全US

基于SAM3超声图像分割的深度学习影像组学预测PTMC中央区淋巴结转移

Prediction of Central Lymph Node Metastasis in Papillary Thyroid Microcarcinoma Using a Deep Learning Radiomics Model Based on SAM3 Automatic Segmentation of Ultrasound Images: A Multicenter Cohort Study.
PubMed 文献 · Acad Radiol · 2026-08-12

本研究回顾性纳入1999例甲状腺微小乳头状癌患者,来自多个中心,利用SAM3自动分割超声图像中的肿瘤,并构建深度学习影像组学模型预测中央区淋巴结转移。结果显示该模型在外部测试组AUC为0.853,决策曲线分析证实其临床应用价值。

要点

  • PTMC超声图像中自动分割肿瘤的Dice相似系数在验证组为0.882±0.145,外部测试组为0.859±0.200。
  • 深度学习影像组学模型预测中央区淋巴结转移在外部测试组AUC为0.853,优于单一影像组学或深度学习模型。
  • 该模型可为PTMC患者术前中央区淋巴结转移风险判断提供无创辅助依据。

核心结论

  • 基于SAM3的深度学习分割在PTMC超声图像自动勾画中取得满意效果,深度学习影像组学模型可无创预测中央区淋巴结转移。

研究设计与样本

  • 回顾性多中心队列研究,收集2017年6月至2025年12月四家医疗中心1859例PTMC患者用于训练和验证。
  • 另收集另一家机构140例患者用于外部测试,所有患者均接受甲状腺切除术及淋巴结清扫。
  • 训练组1674例,验证组185例,外部测试组140例,总评估1999例。
  • 研究基于二维超声图像,利用SAM3进行肿瘤自动分割后提取深度学习和影像组学特征。

关键影像表现/征象

  • SAM3在PTMC超声图像中自动分割肿瘤,验证组Dice相似系数为0.882±0.145,外部测试组为0.859±0.200。

诊断标准与关键数值

  • 影像组学模型预测CLNM的AUC在训练组为0.825,验证组为0.794,外部测试组为0.779。
  • 深度学习模型预测CLNM的AUC在训练组为0.844,验证组为0.825,外部测试组为0.812。
  • 深度学习影像组学模型预测CLNM的AUC在训练组为0.901,验证组为0.875,外部测试组为0.853。
  • 决策曲线分析验证了深度学习影像组学模型的临床应用价值。

临床应用与阅片要点

  • SAM3自动分割可减少PTMC超声图像中肿瘤勾画的人工依赖,提高勾画一致性。
  • 深度学习影像组学模型可作为PTMC术前中央区淋巴结转移风险的辅助评估工具。

局限性

  • 研究为回顾性设计,可能存在选择偏倚。
  • 超声图像采集与分割质量可能受操作者及设备差异影响。

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

RATIONALE AND OBJECTIVES: We aimed to establish a Segment Anything Model 3 (SAM3) based on ultrasound images for automatic papillary thyroid microcarcinoma (PTMC) segmentation and develop and validate a deep learning radiomics (DLR) model based on ultrasound images for noninvasive prediction of central lymph node metastasis (CLNM) in PTMC.

MATERIALS AND METHODS: We retrospectively collected data from 1859 patients with PTMC (1674 and 185 patients in training and validation groups, respectively) who underwent thyroidectomy and lymph node dissection from four medical centers between June 2017 and December 2025. To test the generalizability of the model, we collected data from 140 patients from another facility between June 2017 and December 2025. We automatically segmented tumors in PTMC ultrasound images using SAM3. We then extracted deep learning (DL) and radiomics features from 2D ultrasound images and established a DLR model following dimensionality reduction. We evaluated model utility using receiver operating characteristics, calibration, and decision curve analyses.

RESULTS: We evaluated 1999 patients. The Dice similarity coefficient was 0.882 ± 0.145 and 0.859 ± 0.200 in the validation and external testing groups, respectively. The areas under the curve of the radiomics, DL, and DLR models were 0.825, 0.844, and 0.901 in the training group; 0.794, 0.825, and 0.875 in the validation group; and 0.779, 0.812, and 0.853 in the external testing group, respectively. Decision curve analysis validated the utility of the DLR model.

CONCLUSION: DL-based segmentation built upon SAM3 achieves satisfactory outcomes in automatic PTMC delineation from ultrasound images. The DLR model noninvasively predicts CLNM, supporting clinical decision-making for PTMC.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Song, Zhang, Qin, et al. Prediction of Central Lymph Node Metastasis in Papillary Thyroid Microcarcinoma Using a Deep Learning Radiomics Model Based on SAM3 Automatic Segmentation of Ultrasound Images: A Multicenter Cohort Study. Acad Radiol. 2026. PMID: 42586895. doi:10.1016/j.acra.2026.07.064

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。