切换至 "中华医学电子期刊资源库"

中华医学超声杂志(电子版) ›› 2021, Vol. 18 ›› Issue (02) : 177 -181. doi: 10.3877/cma.j.issn.1672-6448.2021.02.010

所属专题: 文献

浅表器官超声影像学

人工智能S-Detect技术结合钙化特征对甲状腺结节的诊断价值
方明娣1, 彭梅1,(), 毕玉1   
  1. 1. 230601 合肥,安徽医科大学第二附属医院超声诊断科
  • 收稿日期:2020-03-02 出版日期:2021-02-01
  • 通信作者: 彭梅
  • 基金资助:
    安徽省重点研究与开发计划项目(201904a07020068)

Value of artificial intelligent S-Detect technique combined with calcification characteristics in differential diagnosis of thyroid nodules

Mingdi Fang1, Mei Peng1,(), Yu Bi1   

  1. 1. Department of Ultrasound, the Second Affiliated Hospital of Anhui Medical University, Hefei 230601 , China
  • Received:2020-03-02 Published:2021-02-01
  • Corresponding author: Mei Peng
引用本文:

方明娣, 彭梅, 毕玉. 人工智能S-Detect技术结合钙化特征对甲状腺结节的诊断价值[J/OL]. 中华医学超声杂志(电子版), 2021, 18(02): 177-181.

Mingdi Fang, Mei Peng, Yu Bi. Value of artificial intelligent S-Detect technique combined with calcification characteristics in differential diagnosis of thyroid nodules[J/OL]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2021, 18(02): 177-181.

目的

探讨人工智能S-Detect技术结合钙化特征在甲状腺结节良恶性诊断中的价值。

方法

选取2019年7月至2020年1月于安徽医科大学第二附属医院行甲状腺超声检查并行手术治疗的94例患者(94个甲状腺结节)。采用常规超声和S-Detect技术对94例患者的94个甲状腺结节进行检查。以术后病理结果作为金标准,分析超声医师、S-Detect及S-Detect结合钙化特征对甲状腺结节的诊断效能。

结果

经手术病理证实,94个甲状腺结节中,良性37个,恶性57个。超声医师诊断甲状腺结节良恶性的敏感度91.2%,特异度91.8%,准确性91.4%;S-Detect诊断甲状腺结节良恶性的敏感度96.4%,特异度81.1%,准确性90.4%;S-Detect结合钙化特征诊断甲状腺结节的敏感度98.2%,特异度81.8%,准确性92.5.%。超声医师、S-Detect技术及S-Detect结合钙化特征诊断甲状腺结节的ROC曲线下面积分别为0.879、0.864、0.890。S-Detect结合钙化特征的诊断效能优于单独应用常规超声和S-Detect技术(Z=2.020,P=0.043;Z=2.231,P=0.026)。

结论

S-Detect技术结合钙化特征可提高甲状腺结节的诊断效能,值得临床推广应用。

Objective

To assess the value of S-Detect combined with calcification characteristics in the diagnosis of benign and malignant thyroid nodules.

Methods

Ninety-four patients with 94 thyroid nodules were examined by conventional ultrasonography and S-Detect technique at the Second Affiliated Hospital of Anhui Medical University from July 2019 to February 2020, and the diagnostic efficacy of conventional ultrasound, S-Detect,and S-Detect combined with calcification characteristics were analyzed according to the postoperative pathological results.

Results

As confirmed by surgical pathology, of 94 thyroid nodules in 94 patients, 37 were benign and 57 were malignant. The sensitivity, specificity, and accuracy of conventional ultrasound, S-Detect, and S-Detect combined with calcification characteristics in the differential diagnosis of benign and malignant thyroid nodules were 91.2%, 91.8%, and 91.4%, 96.4%, 81.1%, and 90.4%, and 98.2%, 81.8%, and 92.5%, respectively. The areas under the ROC curves of conventional ultrasound, S-Detect, and S-Detect combined with calcification characteristics were 0.879, 0.864, and 0.890, respectively, with the value of S-Detect combined with calcification characteristics being significantly higher than those of conventional ultrasound and S-Detect (Z=2.020, P=0.043; Z=2.231, P= 0.026).

Conclusions

The combination of S-Detect and calcification characteristics can improve the diagnostic efficiency for thyroid nodules.

图1 甲状腺恶性结节超声人工智能检测图。S-Detect自动识别并包络结节,分析结节特征为实性、低回声、垂直位、边缘呈微分叶及毛刺、形态不规则,最后得出结节可能恶性的诊断
图2 甲状腺良性结节超声人工智能检测图。S-Detect自动识别并包络结节,分析结节特征为混合性、高回声/等回声、平行位、边缘光滑、形态规则,最后得出结节可能良性的诊断
表1 超声医师、S-Detect及S-Detect结合钙化特征与病理结果的比较(例)
图3 超声医师、S-Detect与S-Detect结合钙化特征诊断甲状腺结节良恶性的ROC曲线
1
Powers AE, Marcadis AR, Lee M, et al. Changes in trends in thyroid cancer incidence in the United States,1992 to 2016 [J]. JAMA, 2019, 322(24): 2440-2441.
2
Haugen BR, Alexander EK, Bible KC, et al. 2015 American thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer [J]. Thyroid, 2016, 26(1): 128-133.
3
毕腾云, 白文坤, 胡兵. 甲状腺超声钙化形态与甲状腺癌的关系 [J]. 中国超声医学杂志, 2016, 32(6): 481-483.
4
房世保, 仲艳密, 宁春平, 等. 甲状腺癌微钙化的超声分型及临床价值 [J]. 中华超声影像学杂志, 2015, 24(2): 175-176.
5
Kwak JY, Han KH, Yoon JH, et al. Thyroid imaging reporting and data system for US featuresof nodules: a step inestablishing better stratification of cancer risk [J]. Radiology, 2011, 260(3): 892-899.
6
Chang TC. The role of computer-aided detection and diagnosis system in the differential diagnosis of thyroid lesions in ultrasonography [J]. J Med Ultrasound, 2015, 23(4): 177-184.
7
Choi YJ, Baek JH, Park HS, et al. A computer-aided diagnosis system using artificial intelligence for the diagnosis andcharacterization of thyroid nodules on ultrasound:initial clinical assessment [J]. Thyroid, 2017, 27(4): 546-552.
8
Mazurowski MA, Buda M, Saha A, et al. Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI [J]. J Magn Reson Imaging, 2019, 49(4): 949-954.
9
Buda M, Wildman-Tobriner B, Hoang JK, et al. Management of thyroid nodules seen on us images: deep learning may match performance of radiologists [J] . Radiology, 2019, 18(13): 1-7.
10
王丹, 花瞻, 武敬平, 等. 甲状腺结节的超声人工智能诊断 [J]. 中国超声医学杂志, 2019, 35(12): 1070-1072.
11
韩红, 俞清, 赵磊, 等. 超声S-Detect技术在甲状腺肿瘤诊断中的初步应用 [J]. 中华超声影像学杂志, 2018, 27(1): 28-30.
12
Grant EG, Tessler FN, Hoang JK, et al. Thyroid ultrasound reporting lexicon: white paper of the ACR thyroid imaging, reporting and data system (TIRADS) committee [J]. J Am Coll Radiol, 2015, 12(12): 1272-1279.
13
徐上妍, 詹维伟, 周建桥, 等. 超声评估甲状腺结节内钙化的初步探讨 [J]. 中国超声医学杂志, 2012, 28(9): 789-792.
14
杨浩, 尹家保, 吕瑾玉, 等. 超声扫描甲状腺结节钙化特征的临床意义 [J/CD].中华医学超声杂志(电子版), 2011, 8(9): 2038-2041.
15
华翠萍, 王建伟, 郭智兴, 等. 超声在甲状腺结节合并环状钙化的良恶性诊断中的应用 [J/CD]. 中华医学超声杂志(电子版), 2017, 14(10): 755-759.
[1] 王亚红, 蔡胜, 葛志通, 杨筱, 李建初. 颅骨骨膜窦的超声表现一例[J/OL]. 中华医学超声杂志(电子版), 2024, 21(11): 1089-1091.
[2] 章建全, 程杰, 陈红琼, 闫磊. 采用ACR-TIRADS评估甲状腺消融区的调查研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(10): 966-971.
[3] 罗辉, 方晔. 品管圈在提高甲状腺结节细针穿刺检出率中的应用[J/OL]. 中华医学超声杂志(电子版), 2024, 21(10): 972-977.
[4] 杨忠, 时敬业, 邓学东, 姜纬, 殷林亮, 潘琦, 梁泓, 马建芳, 王珍奇, 张俊, 董姗姗. 产前超声在胎儿22q11.2 微缺失综合征中的应用价值[J/OL]. 中华医学超声杂志(电子版), 2024, 21(09): 852-858.
[5] 孙佳丽, 金琳, 沈崔琴, 陈晴晴, 林艳萍, 李朝军, 徐栋. 机器人辅助超声引导下经皮穿刺的体外实验研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(09): 884-889.
[6] 史学兵, 谢迎东, 谢霓, 徐超丽, 杨斌, 孙帼. 声辐射力弹性成像对不可切除肝细胞癌门静脉癌栓患者放射治疗效果的评价[J/OL]. 中华医学超声杂志(电子版), 2024, 21(08): 778-784.
[7] 刘畅, 蒋洁, 胥雪冬, 崔立刚, 王淑敏, 陈文. 北京市海淀区医疗机构甲状腺超声检查及TIRADS分类基线调查[J/OL]. 中华医学超声杂志(电子版), 2024, 21(07): 693-697.
[8] 李洋, 蔡金玉, 党晓智, 常婉英, 巨艳, 高毅, 宋宏萍. 基于深度学习的乳腺超声应变弹性图像生成模型的应用研究[J/OL]. 中华医学超声杂志(电子版), 2024, 21(06): 563-570.
[9] 唐金侨, 叶宇佳, 王港, 赵彬, 马艳宁. 医学影像学检查方法在颞下颌关节紊乱病中临床应用研究进展[J/OL]. 中华口腔医学研究杂志(电子版), 2024, 18(06): 406-411.
[10] 王秋生. 胆道良性疾病诊疗策略[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 779-782.
[11] 李浩, 陈棋帅, 费发珠, 张宁伟, 李元东, 王硕晨, 任宾. 慢性肝病肝纤维化无创诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(09): 863-867.
[12] 谭瑞义. 小细胞骨肉瘤诊断及治疗研究现状与进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 781-784.
[13] 孙铭远, 褚恒, 徐海滨, 张哲. 人工智能应用于多发性肺结节诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 785-790.
[14] 王子阳, 王宏宾, 刘晓旌. 血清标志物对甲胎蛋白阴性肝细胞癌诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 677-681.
[15] 陈慧, 邹祖鹏, 周田田, 张艺丹, 张海萍. 皮肤镜对头皮红斑性皮肤病辅助鉴别诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 692-698.
阅读次数
全文


摘要