| 田艳,罗亦铭,牛紫轩,李惠霖,王建林,张波.基于深度学习颈部淋巴结超声网络模型诊断甲状腺乳头状癌颈部淋巴结转移[J].中国医学影像技术,2025,41(9):1502~1505 |
| 基于深度学习颈部淋巴结超声网络模型诊断甲状腺乳头状癌颈部淋巴结转移 |
| Cervical lymph node ultrasound network model based on deep learning for diagnosing cervical lymph node metastasis of papillary thyroid carcinoma |
| 投稿时间：2025-05-14 修订日期：2025-08-31 |
| DOI：10.13929/j.issn.1003-3289.2025.09.010 |
| 中文关键词: 甲状腺癌,乳头状|淋巴结|肿瘤转移|超声检查|深度学习 |
| 英文关键词:thyroid cancer, papillary|lymph nodes|neoplasm metastasis|ultrasonography|deep learning |
| 基金项目: |
| 作者 | 单位 | E-mail | | 田艳 | 中日友好医院超声医学科, 北京 100029 | | | 罗亦铭 | 中国核电工程有限公司, 北京 100840 | | | 牛紫轩 | 中日友好医院超声医学科, 北京 100029 | | | 李惠霖 | 中国医学科学院北京协和医学院, 北京 100730 | | | 王建林 | 北京化工大学信息科学与技术学院, 北京 100029 | | | 张波 | 中日友好医院超声医学科, 北京 100029
中日友好医院呼吸中心, 国家呼吸医学中心, 呼吸和共病全国重点实验室, 国家呼吸疾病临床研究中心, 中国医学科学院呼吸病学研究院, 北京 100029 | thyroidus@163.com |
|
| 摘要点击次数: 116 |
| 全文下载次数: 48 |
| 中文摘要: |
| 目的 观察基于深度学习(DL)的颈部淋巴结超声网络模型诊断甲状腺乳头状癌(PTC)颈部淋巴结转移的价值。方法 回顾性纳入444例超声提示颈部可疑淋巴结肿大的PTC患者;根据细针穿刺抽吸病理及甲状腺球蛋白检测结果分为转移组(n=253)与非转移组(n=191)。将1 754幅颈部淋巴结超声图像按8∶1∶1分为训练集(n=1 404)、验证集(n=175)及测试集(n=175);提取颈部淋巴结的超声特征,利用DL建立超声网络模型,观察其诊断淋巴结转移的效能。结果 超声网络模型诊断验证集PTC颈部淋巴结转移的敏感度为93.06%、特异度为97.05%、准确率为95.04%、曲线下面积为0.858,在测试集分别为86.14%、78.67%、88.49%及0.828。结论 基于DL的颈部淋巴结超声网络模型有助于诊断PTC颈部淋巴结转移。 |
| 英文摘要: |
| Objective To observe the value of cervical lymph node ultrasound network model based on deep learning (DL) for diagnosing cervical lymph node metastasis of papillary thyroid carcinoma (PTC). Methods Totally 444 PTC patients with suspected cervical lymph node enlargement on ultrasonography were retrospectively enrolled and divided into metastasis group (n=253) and non-metastasis group (n=191) based on fine needle aspiration pathology and thyroglobulin detection. And 1 754 cervical lymph node ultrasonic images were divided into training set (n=1 404), validation set (n=175) and test set (n=175) at the ratio of 8∶1∶1. Ultrasonic features of cervical lymph nodes were extracted, then ultrasound network model was established using DL, and the diagnostic efficacy of this model for diagnosing lymph node metastasis was analyzed. Results The sensitivity, specificity, accuracy and area under the curve of ultrasound network model for diagnosing cervical lymph node metastasis of PTC was 93.06%, 97.05%, 95.04% and 0.858 in validation set, which was 86.14%, 78.67%, 88.49% and 0.828 in test set, respectively. Conclusion Cervical lymph node ultrasound network model based on DL was helpful for diagnosing cervical lymph node metastasis of PTC. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
