Cordes Michael, Götz Theresa Ida, Lang Elmar Wolfgang, Coerper Stephan, Kuwert Torsten, Schmidkonz Christian
Radiologisch-Nuklearmedizinisches Zentrum, Martin-Richter-Str. 43, 90489, Nürnberg, Germany.
Nuklearmedizinische Klinik, Universitätsklinikum Erlangen, Erlangen, Germany.
Thyroid Res. 2021 Jun 29;14(1):16. doi: 10.1186/s13044-021-00107-z.
Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain characteristics observable by ultrasound have recently been identified that may indicate malignancy. This retrospective cohort study was conducted to test the hypothesis that advanced thyroid carcinomas show distinctive clinical and sonographic characteristics. Using a neural network model as proof of concept, nine clinical/sonographic features served as input.
All 96 study enrollees had histologically confirmed thyroid carcinomas, categorized (n = 32, each) as follows: group 1, advanced carcinoma (ADV) marked by local invasion or distant metastasis; group 2, non-advanced papillary carcinoma (PTC); or group 3, non-advanced follicular carcinoma (FTC). Preoperative ultrasound profiles were obtained via standardized protocols. The neural network had nine input neurons and one hidden layer.
Mean age and the number of male patients in group 1 were significantly higher compared with groups 2 (p = 0.005) or 3 (p < 0.001). On ultrasound, tumors of larger volume and irregular shape were observed significantly more often in group 1 compared with groups 2 (p < 0.001) or 3 (p ≤ 0.01). Network accuracy in discriminating advanced vs. non-advanced tumors was 84.4% (95% confidence interval [CI]: 75.5-91), with positive and negative predictive values of 87.1% (95% CI: 70.2-96.4) and 92.3% (95% CI: 83.0-97.5), respectively.
Our study has shown some evidence that advanced thyroid tumors demonstrate distinctive clinical and sonographic characteristics. Further prospective investigations with larger numbers of patients and multicenter design should be carried out to show whether a neural network incorporating these features may be an asset, helping to classify malignancies of the thyroid gland.
超声是检测和分类甲状腺结节的一线成像方式。最近已确定某些超声可观察到的特征可能提示恶性肿瘤。本回顾性队列研究旨在检验晚期甲状腺癌具有独特临床和超声特征这一假设。以神经网络模型作为概念验证，九个临床/超声特征作为输入。
所有96名研究参与者均有组织学确诊的甲状腺癌，分为以下三组（每组n = 32）：第1组，以局部侵犯或远处转移为特征的晚期癌（ADV）；第2组，非晚期乳头状癌（PTC）；或第3组，非晚期滤泡状癌（FTC）。通过标准化方案获取术前超声图像。神经网络有九个输入神经元和一个隐藏层。
与第2组（p = 0.005）或第3组（p < 0.001）相比，第1组的平均年龄和男性患者数量显著更高。在超声检查中，与第2组（p < 0.001）或第3组（p≤0.01）相比，第1组中体积较大和形状不规则的肿瘤明显更常见。区分晚期与非晚期肿瘤的网络准确率为84.4%（95%置信区间[CI]：75.5 - 91），阳性和阴性预测值分别为87.1%（95% CI：70.2 - 96.4）和92.3%（95% CI：83.0 - 97.5）。
我们的研究已显示出一些证据，表明晚期甲状腺肿瘤具有独特的临床和超声特征。应进行更多患者参与的多中心前瞻性研究，以表明纳入这些特征的神经网络是否有助于甲状腺恶性肿瘤的分类。
