The Department of General Surgery, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, China.
The Fourth Clinical Medical College, Zhejiang Chinese Medical University, Hangzhou, China.
Endocrine. 2024 Jan;83(1):118-126. doi: 10.1007/s12020-023-03461-0. Epub 2023 Aug 5.
To investigate the application of machine learning (ML) model-based thyroid ultrasound radiomics in the evaluation of malignancy in partially cystic thyroid nodules (PCTNs).
One hundred and ninety-two patients with 197 nodules PCTNs from January 2020 to December 2020 were retrospectively analyzed. Radiomics features were extracted based on hand-crafted features from the ultrasound images, and machine learning methods were used to build a classification model by radiomics features. The least absolute shrinkage and selection operator regression was applied to select the features of nonzero coefficients from radiomics features. The prediction performance of the established model was mainly evaluated by the area under the curve (AUC) and accuracy, sensitivity, and specificity.
Nineteen radiomics features were extracted from the original images for each nodule. Eight ML classifiers were able to differentiate malignancy in PCTNs. The AUC, accuracy, sensitivity, and specificity of k-Nearest Neighbor (KNN) model were 0.909, 82.95%, 83.33%, and 89.90%, respectively, on the test cohort. The comparative result showed statistically equivalent performance for thyroid nodule diagnosis based on image fusion and single image. In addition, the ML-Based ultrasound radiomics system showed a better AUC as compared with ACR TI-RADS model and the ultrasound features model.
The novel ultrasonic-based ML model has an important clinical value for predicting malignancy in PCTNs. It can provide clinicians with a preoperative non-invasive primary screening method for PCTN diagnosis to avoid unnecessary medical investment and improve treatment outcomes.
探讨基于机器学习（ML）模型的甲状腺超声放射组学在部分囊性甲状腺结节（PCTNs）恶性评估中的应用。
回顾性分析 2020 年 1 月至 2020 年 12 月期间 192 例 197 个部分囊性甲状腺结节患者的资料。基于超声图像的手工特征提取放射组学特征，并采用放射组学特征的机器学习方法构建分类模型。采用最小绝对值收缩和选择算子回归法从放射组学特征中选择非零系数的特征。通过曲线下面积（AUC）和准确率、敏感度、特异度来主要评价所建立模型的预测性能。
为每个结节从原始图像中提取了 19 个放射组学特征。八种 ML 分类器可区分 PCTNs 的良恶性。在测试队列中，k-最近邻（KNN）模型的 AUC、准确率、敏感度和特异度分别为 0.909、82.95%、83.33%和 89.90%。对比结果表明，基于图像融合和单图像的甲状腺结节诊断具有相当的性能。此外，与 ACR TI-RADS 模型和超声特征模型相比，基于 ML 的超声放射组学系统具有更好的 AUC。
基于新型超声的 ML 模型对预测 PCTNs 的恶性具有重要的临床价值。它可为临床医生提供 PCTN 诊断的术前非侵入性初步筛选方法，避免不必要的医疗投资并改善治疗结果。
