Zhong Lichang, Shi Lin, Lai Jinyu, Hu Yuhong, Gu Liping
Department of Ultrasound in Medicine, Shanghai Sixth People's Hospital Affiliated to Medical College of Shanghai Jiao Tong University, Shanghai Institute of Ultrasound in Medicine, Shanghai, China.
Department of Ultrasound in Medicine, Tinglin Hospital, Tongji Medical Group, Shanghai, China.
Gland Surg. 2024 Nov 30;13(11):1954-1964. doi: 10.21037/gs-24-310. Epub 2024 Nov 24.
The management of thyroid nodules diagnosed as Bethesda III by fine-needle aspiration presents certain challenges, and there is an urgent need for a non-invasive and accurate method for early identification of the benign or malignant nature of Bethesda III nodules. Our objective is to develop and validate a clinical-radiomics nomogram based on preoperative ultrasound (US) images and clinical features, for predicting the malignancy of thyroid nodules with indeterminate cytology (Bethesda III).
Between June 2017 and June 2022, we conducted a retrospective study on 274 patients with surgically confirmed indeterminate cytology (Bethesda III) across two separate medical centers in Shanghai. The training and internal validation sets were comprised of 136 and 58 patients, respectively, all sourced from Shanghai's Sixth People's Hospital. To facilitate external test, a further 80 patients were selected from Tinglin Hospital. Utilizing preoperative US data, we obtained imaging markers for radiomic features. After feature selection, we developed a comprehensive diagnostic model to evaluate the predictive value for Bethesda III benign and malignant cases. The model's diagnostic accuracy, calibration, and clinical applicability were systematically assessed.
The results showed that the prediction model, which integrated US radiomics, and clinical risk features, exhibited superior stability in distinguishing between benign and malignant indeterminate thyroid nodules (Bethesda III). In the external test set, the area under the curve (AUC) was 0.824 [95% confidence interval (CI): 0.718-0.929], and the accuracy, sensitivity, specificity, precision, and recall were 0.775, 0.731, 0.796, 0.633, and 0.731, respectively.
An integrated model, utilizing US radiomics and clinical risk features, effectively discriminates between benign and malignant indeterminate thyroid nodules (Bethesda III), thereby minimizing the need for unnecessary diagnostic surgeries and subsequent complications.
细针穿刺诊断为贝塞斯达Ⅲ类的甲状腺结节的管理面临一定挑战，迫切需要一种非侵入性且准确的方法来早期识别贝塞斯达Ⅲ类结节的良恶性。我们的目标是基于术前超声（US）图像和临床特征开发并验证一种临床影像组学列线图，以预测细胞学结果不确定（贝塞斯达Ⅲ类）的甲状腺结节的恶性程度。
2017年6月至2022年6月，我们对上海两个独立医疗中心的274例手术确诊为细胞学结果不确定（贝塞斯达Ⅲ类）的患者进行了回顾性研究。训练集和内部验证集分别由136例和58例患者组成，均来自上海第六人民医院。为便于外部测试，从亭林医院又选取了80例患者。利用术前超声数据，我们获取了影像组学特征的成像标记。经过特征选择后，我们开发了一个综合诊断模型来评估对贝塞斯达Ⅲ类良性和恶性病例的预测价值。系统评估了该模型的诊断准确性、校准度和临床适用性。
结果表明，整合了超声影像组学和临床风险特征的预测模型在区分良性和恶性不确定甲状腺结节（贝塞斯达Ⅲ类）方面表现出卓越的稳定性。在外部测试集中，曲线下面积（AUC）为0.824 [95%置信区间（CI）：0.718 - 0.929]，准确性、敏感性、特异性、阳性预测值和召回率分别为0.775、0.731、0.796、0.633和0.731。
利用超声影像组学和临床风险特征的综合模型能有效区分良性和恶性不确定甲状腺结节（贝塞斯达Ⅲ类），从而减少不必要的诊断性手术及后续并发症的需求。
