Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA; Department of Ultrasound, Peking University First Hospital, Beijing, China.
Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA; Northeastern University, Boston, Massachusetts, USA.
Ultrasound Med Biol. 2022 Aug;48(8):1547-1554. doi: 10.1016/j.ultrasmedbio.2022.03.020. Epub 2022 Jun 1.
To develop an ultrasound-based machine learning classifier to diagnose benignity within indeterminate thyroid nodules (ITNs) by fine-needle aspiration, 180 patients with 194 ITNs (Bethesda classes III, IV and V) undergoing surgery over a 5-y study period were analyzed. The data set was randomly divided into training and testing data sets with 155 and 39 ITNs, respectively. All nodules were evaluated by ultrasound using the American College of Radiology Thyroid Imaging Reporting and Data System by manually scoring composition, echogenicity, shape, margin and echogenic foci. Nodule size, participant age and patient sex were recorded. A support vector machine (SVM) model with a cost-sensitive approach was developed using the aforementioned eight parameters with surgical histopathology as the reference standard. Surgical pathology determined 90 (46.4%) ITNs were malignant and 104 (53.6%) were benign. The SVM model classified 14 nodules as benign in the testing data set, of which 13 were correct (sensitivity = 93.8%, specificity = 56.5%). Considering malignancy prevalence by Bethesda group, the negative predictive values of this model for Bethesda III and IV categories were 93.9% and 93. 8%, respectively. The high negative predictive value of the SVM ultrasound-based model suggests a pathway by which surgical excision of Bethesda III and IV ITNs classified as benign may be avoided.
为了开发一种基于超声的机器学习分类器，通过细针抽吸来诊断不确定甲状腺结节（ITN）的良性，对 180 名患者的 194 个 ITN（Bethesda 类别 III、IV 和 V）进行了研究，这些患者在 5 年的研究期间接受了手术。数据集随机分为训练数据集和测试数据集，分别有 155 个和 39 个 ITN。所有结节均使用美国放射学院甲状腺成像报告和数据系统（ACR TI-RADS）进行超声评估，通过手动评分结节的成分、回声、形状、边界和回声焦点。记录了结节大小、参与者年龄和患者性别。使用上述 8 个参数和成本敏感方法开发了支持向量机（SVM）模型，以手术组织病理学为参考标准。手术病理确定 90 个（46.4%）ITN 为恶性，104 个（53.6%）为良性。SVM 模型在测试数据集中将 14 个结节分类为良性，其中 13 个是正确的（敏感性为 93.8%，特异性为 56.5%）。考虑到 Bethesda 组的恶性患病率，该模型对 Bethesda III 和 IV 类别的阴性预测值分别为 93.9%和 93.8%。SVM 超声模型的高阴性预测值表明，对于被分类为良性的 Bethesda III 和 IV ITN，可以通过手术切除来避免。
