超声影像组学特征与常规临床超声指标联合模型在结核性淋巴结与转移性淋巴结鉴别诊断中的应用研究

doi:10.19871/j.cnki.xfcrbzz.2026.03.010

新发传染病电子杂志 ›› 2026, Vol. 11 ›› Issue (3): 55-60.doi: 10.19871/j.cnki.xfcrbzz.2026.03.010

超声影像组学特征与常规临床超声指标联合模型在结核性淋巴结与转移性淋巴结鉴别诊断中的应用研究

黄裕兰¹, 潘彦汐², 黄颖华¹, 黄小桂¹, 蒙能芳¹, 蒋开茂¹, 卢亦波²

1.南宁市第四人民医院,广西艾滋病临床治疗中心(南宁)超声诊疗科,广西南宁 530013;
2.南宁市第四人民医院,广西艾滋病临床治疗中心(南宁)医学影像科,广西南宁 530013

收稿日期:2026-02-12 出版日期:2026-06-30 发布日期:2026-07-17
通讯作者: 卢亦波,Email：13768415203@139.com
基金资助:
1.南宁市兴宁区发展改革和科学技术局项目（2022A11）;2.广西壮族自治区中医药管理局科研项目（GXZYA20250875）

Application of a combined model of ultrasound radiomics features and routine clinical ultrasound indicators in the differential diagnosis of tuberculous lymph nodes and metastatic lymph nodes

Huang Yulan¹, Pan Yanxi², Huang Yinghua¹, Huang Xiaogui¹, Meng Nengfang¹, Jiang Kaimao¹, Lu Yibo²

1. Department of Ultrasound, The Fourth People's Hospital of Nanning, the Clinical Treatment Center for AIDS of Guangxi Nanning, Guangxi Nanning 530013, China;
2. Department of Medical Imaging, The Fourth People's Hospital of Nanning, the Clinical Treatment Center for AIDS of Guangxi Nanning, Guangxi Nanning 530013, China

Received:2026-02-12 Online:2026-06-30 Published:2026-07-17

摘要/Abstract

摘要： 目的探讨超声影像组学特征与常规临床超声指标构建的联合模型对结核性淋巴结与转移性淋巴结的鉴别诊断效能,为临床提供更可靠的辅助诊断依据。方法回顾性收集2020年1月至2024年12月在南宁市第四人民医院确诊的结核性淋巴结患者346例、转移性淋巴结患者109例的完整超声影像及临床资料。按7∶3采用随机数字表法分为训练集(结核性淋巴结242例,转移性淋巴结76例)与测试集(结核性淋巴结104例,转移性淋巴结33例)。对病灶区域进行勾画并筛选出具有统计学意义的超声影像组学特征,构建超声影像组学模型。通过差异分析筛选出具有统计学意义的常规临床超声指标构建临床模型。融合超声影像组学特征与常规临床超声指标构建联合模型,并对联合模型诊断效能进行评估。结果在训练集和测试集内部,年龄、性别、最小短径、内部回声在结核性淋巴结与转移性淋巴结两组间比较差异均有统计学意义（P<0.05）,通过最小绝对收缩和选择算子回归分析,最终从提取特征中筛选出8个超声影像组学特征。训练集中,联合模型的曲线下面积（area under the curve,AUC）为0.872（95%CI：0.826~0.918）、敏感度为0.730、特异度为0.868,测试集上AUC为0.875（95%CI：0.805~0.945）、敏感度为0.765、特异度为0.833。DeLong检验显示,无论在训练集还是测试集,联合模型的AUC均显著高于超声影像组学模型与临床模型（均P<0.05）,提示该联合模型具备较高的临床应用潜力。结论基于超声影像组学特征与常规临床超声指标构建的联合模型在结核性淋巴结与转移性淋巴结具有良好的鉴别诊断效能。

关键词: 结核性淋巴结, 转移性淋巴结, 超声影像组学, 鉴别, 诊断

Abstract: Objective To evaluate the diagnostic efficacy of a combined model based on ultrasound radiomics features and conventional sonographic features in differentiating tuberculous lymph nodes from metastatic lymph nodes, so as to provide more reliable evidence for clinical auxiliary diagnosis. Method A total of 346 patients with tuberculous lymph nodes and 109 patients with metastatic lymph nodes diagnosed in the Fourth People's Hospital of Nanning from January 2020 to December 2024 were retrospectively enrolled. Complete ultrasound images and clinical data were collected. Patients were divided into training set (242 tuberculous lymph nodes, 76 metastatic lymph nodes) and test set (104 tuberculous lymph nodes, 33 metastatic lymph nodes) at a 7:3 ratio using a random number table method. Lesion regions of interest (ROI) were delineated, statistically significant ultrasound radiomics features were screened out to establish the radiomics model. Conventional sonographic features with statistical differences were selected to construct the clinical model. The combined model was established by integrating radiomics features and conventional sonographic features, and its diagnostic performance was assessed. Result Age, gender, minimal short diameter and internal echo showed statistically significant differences between tuberculous and metastatic lymph nodes in both training and test sets(P<0.05). Finally, 8 radiomics features were screened out through LASSO regression. In the training set, the AUC of the combined model was 0.872 (95%CI:0.826-0.918), the sensitivity was 0.730, and the specificity was 0.868. In the test set, the AUC was 0.875 (95%CI:0.805-0.945), the sensitivity was 0.765, and the specificity was 0.833. DeLong test showed that the AUC of the combined model was significantly higher than that of the radiomics model and clinical model in both sets (all P<0.05), indicating favorable clinical application value. Conclusion The combined model constructed by ultrasound radiomics features and conventional sonographic features exhibits satisfactory diagnostic performance in differentiating tuberculous lymph nodes from metastatic lymph nodes.

Key words: Tuberculous cervical lymph nodes, Metastatic lymph nodes, Ultrasound radiomics, Differentiation, Diagnosis

中图分类号:

R51
R445.1

黄裕兰, 潘彦汐, 黄颖华, 黄小桂, 蒙能芳, 蒋开茂, 卢亦波. 超声影像组学特征与常规临床超声指标联合模型在结核性淋巴结与转移性淋巴结鉴别诊断中的应用研究[J]. 新发传染病电子杂志, 2026, 11(3): 55-60.

Huang Yulan, Pan Yanxi, Huang Yinghua, Huang Xiaogui, Meng Nengfang, Jiang Kaimao, Lu Yibo. Application of a combined model of ultrasound radiomics features and routine clinical ultrasound indicators in the differential diagnosis of tuberculous lymph nodes and metastatic lymph nodes[J]. Electronic Journal of Emerging Infectious Diseases, 2026, 11(3): 55-60.

参考文献

[1] 钟明, 李刚, 王宁, 等. 颈部淋巴结结核患者疾病进展的危险因素分析[J/CD]. 新发传染病电子杂志, 2024, 9(1): 42-46.
[2] CATAÑO JC, ROBLEDO J. Tuberculous Lymphadenitis and Parotitis[J]. Microbiol Spectr, 2016, 4(6):e00287.
[3] JI H, HU C, YANG X, et al.Lymph node metastasis in cancer progression: molecular mechanisms, clinical significance and therapeutic interventions[J]. Signal Transduct Target Ther, 2023, 8(1): 367.
[4] 詹玲, 陈创, 孙圣荣. 甲状腺乳头状癌淋巴结转移数目与临床病理特征的相关性分析[J]. 中华实用诊断与治疗杂志, 2020,34(12): 1206-1208.
[5] 张雪云, 聂芳, 吕文豪, 等. 超声造影对结核性淋巴结与转移性淋巴结的鉴别诊断价值[J]. 中国超声医学杂志, 2018, 34(5): 403-406.
[6] LIU Y, CHEN J, ZHANG C, et al.Ultrasound-Based Radiomics Can Classify the Etiology of Cervical Lymphadenopathy: A Multi-Center Retrospective Study[J]. Front Oncol, 2022,12: 856605.
[7] CHEN Y, JIANG J, SHI J, et al.Dual-mode ultrasound radiomics and intrinsic imaging phenotypes for diagnosis of lymph node lesions[J]. Ann Transl Med, 2020, 8(12): 742.
[8] YENILMEZ E, ÖZAKNSEL D, KÖSE A, et al. Diagnostic approach of tuberculous lymphadenitis in a multicenter study[J]. J Infect Dev Ctries, 2024, 18(5): 742-750.
[9] 南大鹏. 超声鉴别诊断颈部结核性淋巴结和转移性淋巴结的价值[J]. 中国医疗器械信息, 2017, 23(24): 109-110.
[10] LI L, HE L, XIONG M, et al.Diagnostic value of contrast-enhanced ultrasound combined with serum procalcitonin in tuberculous lymph nodes and metastatic lymph nodes[J]. Clinics (Sao Paulo), 2025, 80: 100541.
[11] BASSIOUNI M, KANG G, OLZE H, et al.The Diagnostic Yield of Excisional Biopsy in Cervical Lymphadenopathy: A Retrospective Analysis of 158 Biopsies in Adults[J]. Ear Nose Throat J, 2023, 102(10): 645-649.
[12] 张琦, 庄连婷, 李家兴, 等. 常规超声联合超声造影对颈部实性淋巴结良恶性的鉴别诊断[J]. 中国医学影像学杂志, 2021, 29(1): 14-18.
[13] 夏从乐, 袁婷. 超声鉴别诊断颈部浅表淋巴结良恶性的临床价值[J]. 中国现代医生, 2021, 59(36): 109-111.
[14] 林小勇, 袁艺, 刘新华. 探讨颈部结核性淋巴结与转移性淋巴结在超声声像图中的特点[J]. 影像研究与医学应用, 2020, 4(2): 64-65.
[15] ZHENG X, YAO Z, HUANG Y, et al.Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer[J]. Nat Commun, 2020, 11(1): 1236.
[16] JIANG M, LI CL, LUO XM, et al.Ultrasound-based deep learning radiomics in the assessment of pathological complete response to neoadjuvant chemotherapy in locally advanced breast cancer[J]. Eur J Cancer, 2021, 147: 95-105.
[17] 郭建峰, 宋鑫洋, 沈天赐, 等. 基于多模态影像组学联合机器学习模型预测甲状腺乳头状癌颈部淋巴结转移的价值[J]. 放射学实践, 2024, 39(9): 1152-1157.
[18] ATNAFU A, WASSIE L, TILAHUN M, et al.Cytomorphological patterns and clinical features of presumptive tubercular lymphadenitis patients and their comparison with bacteriological detection methods: a cross-sectional study[J]. BMC Infect Dis, 2024,24(1): 684.
[19] LUND AW.Lymph node metastasis: An immunological burden[J]. J Exp Med, 2023, 220(9):e20230666.

超声影像组学特征与常规临床超声指标联合模型在结核性淋巴结与转移性淋巴结鉴别诊断中的应用研究

Application of a combined model of ultrasound radiomics features and routine clinical ultrasound indicators in the differential diagnosis of tuberculous lymph nodes and metastatic lymph nodes

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	周永, 李凤娟, 阮超, 蔡华锋, 李雨辰. 增强现实导航与传统支气管镜引导肺泡灌洗对菌阴肺结核诊断效能的随机对照研究[J]. 新发传染病电子杂志, 2026, 11(3): 7-12.
[2]	刘夏, 邹俊, 卢亦波, 覃小英, 许秋娜, 梁翠金, 赵蕊, 蓝健, 肖秋叶, 黄田, 韦垠朵, 覃金梅, 阳世雄. 实时荧光定量PCR在马尔尼菲篮状菌感染诊断与疗效监测中的临床价值[J]. 新发传染病电子杂志, 2026, 11(3): 24-29.
[3]	赖晓宇, 陈珣珣, 廖庆华, 温文沛, 吴粤. 结核后非结核分枝杆菌肺病的流行病学及诊疗新进展[J]. 新发传染病电子杂志, 2026, 11(3): 81-88.
[4]	浦英, 杞敏, 魏佳璐, 干玮, 肖方, 寸新华, 李翔. CT征象联合血常规指标在布鲁氏菌性脊柱炎与化脓性脊柱炎鉴别诊断中的应用价值研究[J]. 新发传染病电子杂志, 2026, 11(2): 11-16.
[5]	张丽慧, 苏宇, 靖瑞峰. 内蒙古自治区布鲁氏菌病流行病学现状、诊断挑战及防控策略研究进展[J]. 新发传染病电子杂志, 2026, 11(2): 76-82.
[6]	郑婷, 李小玲, 徐玉琪, 蔡建新. 血清生存素、4-羟基壬烯醛、高半胱氨酸蛋白61对儿童社区获得性肺炎诊断和病情评估的价值分析[J]. 新发传染病电子杂志, 2025, 10(5): 6-11.
[7]	赵云, 徐芳, 王琛, 盛芳. 分子诊断技术联合相关细胞因子表达水平检测对肺结核与非结核分枝杆菌肺病的鉴别诊断价值分析[J]. 新发传染病电子杂志, 2025, 10(5): 53-58.
[8]	詹梅, 赵颂涛, 郭建琼, 李同心, 杨松. 《WHO无症状结核病咨询报告》解读[J]. 新发传染病电子杂志, 2025, 10(5): 100-104.
[9]	刘晓宁, 唐飞, 梅恒, 刘盛盛, 章鑫丽, 张良柱, 马方方, 李晔. 中性粒细胞百分比、血红蛋白及D-二聚体联合检测在肺结核合并结核性多浆膜腔积液中的诊断价值分析[J]. 新发传染病电子杂志, 2025, 10(4): 34-39.
[10]	刘瑞花, 金慧芳, 王爱霞, 郑伟, 刘哲芳, 陈琛, 宋雪飞, 乌力吉, 王芙蓉. 《WHO结核病综合指南模块3——诊断》解读[J]. 新发传染病电子杂志, 2025, 10(4): 94-104.
[11]	张琳, 肖海浩, 李天义, 苏雯婕. 疑似肺结核的机化性肺炎患者临床及病理特征分析[J]. 新发传染病电子杂志, 2025, 10(3): 24-28.
[12]	李秋萍, 姚伟明, 冯世艳, 林元龙, 王福祥. 耳念珠菌感染的研究进展[J]. 新发传染病电子杂志, 2025, 10(3): 78-83.
[13]	全娜丽, 彭美, 卢远彬, 王慧婷, 林思强. 裂隙有核细胞在百日咳患者中的表达及诊断价值研究进展[J]. 新发传染病电子杂志, 2025, 10(2): 89-93.
[14]	张雅曦, 杨倩婷, 张洁云, 张明霞, 熊欣雨, 陈骑. 组织荧光定量聚合酶链反应联合多方法学在淋巴结结核诊断中的临床应用[J]. 新发传染病电子杂志, 2025, 10(1): 8-11.
[15]	温立旻, 李晔, 李恒星, 林伟, 侯代伦. CT在肺癌与肺癌合并肺结核鉴别诊断中的应用价值[J]. 新发传染病电子杂志, 2025, 10(1): 17-21.