Department of Radiology, Shunde Hospital of Southern Medical University (The First People's Hospital of Shunde), No.1, Penglai Road, Daliang District, Shunde, Foshan, Guangdong, People's Republic of China.
Department of Ultrasound, Shunde Hospital of Southern Medical University (The First People's Hospital of Shunde), Foshan, Guangdong, People's Republic of China.
Eur Radiol. 2019 Mar;29(3):1518-1526. doi: 10.1007/s00330-018-5715-5. Epub 2018 Sep 12.
The aim of this study was to develop an ultrasound-based nomogram to improve the diagnostic accuracy of the identification of malignant thyroid nodules.
A total of 1675 histologically proven thyroid nodules (1169 benign, 506 malignant) were included in this study. The nodules were grouped into the training dataset (n = 700), internal validation dataset (n = 479), or external validation dataset (n = 496). The grayscale ultrasound features included the nodule size, shape, aspect ratio, echogenicity, margins, and calcification pattern. We applied least absolute shrinkage and selection operator (lasso) regression to select the strongest features for the nomogram. Nomogram discrimination (area under the receiver operating characteristic curve, AUC) and calibration were assessed. The nomogram was subjected to bootstrapping validation (1000 bootstrap resamples) to calculate a mean AUC and 95% confidence interval (CI).
The nomogram showed good discrimination in the training dataset, with an AUC of 0.936 (95% CI: 0.918-0.953) and good calibration. Application of the nomogram to the internal validation dataset also resulted in good discrimination (AUC: 0.935; 95% CI, 0.915-0.954) and good calibration. The model tested in an external validation dataset demonstrated a lower AUC of 0.782 (95% CI: 0.776-0.789).
This ultrasound-based nomogram can be used to quantify the probability of malignant thyroid nodules.
• Ultrasound examination is helpful in the differential diagnosis of malignant and benign thyroid nodules. • However, ultrasound accuracy relies heavily on examiner experience. • A less subjective diagnostic model is desired, and the developed nomogram for thyroid nodules showed good discrimination and good calibration.
本研究旨在建立一种基于超声的列线图，以提高恶性甲状腺结节的诊断准确性。
本研究共纳入 1675 例经组织学证实的甲状腺结节（1169 例良性，506 例恶性）。这些结节被分为训练数据集（n=700）、内部验证数据集（n=479）或外部验证数据集（n=496）。灰阶超声特征包括结节大小、形状、纵横比、回声性、边界和钙化模式。我们应用最小绝对收缩和选择算子（lasso）回归来选择列线图的最强特征。评估了列线图的鉴别能力（接受者操作特征曲线下面积，AUC）和校准。该列线图通过自举验证（1000 次自举重采样）来计算平均 AUC 和 95%置信区间（CI）。
该列线图在训练数据集中具有良好的鉴别能力，AUC 为 0.936（95%CI：0.918-0.953），校准良好。该列线图在内部验证数据集中的应用也产生了良好的鉴别能力（AUC：0.935；95%CI，0.915-0.954）和良好的校准。在外部验证数据集中测试的模型显示 AUC 较低，为 0.782（95%CI：0.776-0.789）。
该基于超声的列线图可用于量化恶性甲状腺结节的概率。
• 超声检查有助于鉴别诊断良恶性甲状腺结节。• 然而，超声的准确性很大程度上依赖于检查者的经验。• 需要一种主观性更小的诊断模型，所开发的甲状腺结节列线图具有良好的鉴别能力和校准能力。
