Department of Ultrasound, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China.
Key Laboratory of Modern Acoustics (MOE), Department of Physics, Collaborative Innovation Center of Advanced Microstructure, Nanjing University, Nanjing 210093, China.
Ultrasonics. 2019 Nov;99:105951. doi: 10.1016/j.ultras.2019.105951. Epub 2019 Jun 24.
This study explored the use of backscattered radiofrequency ultrasound signals combined with artificial neural network (ANN) technology to differentiate benign and malignant thyroid nodules, in comparison with conventional ultrasound techniques. The proposed method uses the gray level co-occurrence matrix algorithm and principal component analysis to identify principal characteristics for use as inputs in the ANN. The dataset consisted of 131 ultrasound images, of which 59 were benign and 72 were malignant, as determined by subsequent surgeries. The nodules were divided randomly into training, validation, and testing groups. Receiver operating characteristic curves (ROC) were drawn to compare the diagnostic efficiency of the ANN when applied to radiofrequency and conventional ultrasound images. The sensitivity, specificity, and accuracy of the ANN in predicting malignancy from the radiofrequency ultrasound images were 100, 91.5, and 96.2%, respectively; from conventional ultrasound, the corresponding values were 94.4, 93.2, and 93.9%, respectively. The area under the receiver operating characteristic curve (AUC) was also higher for radiofrequency than conventional ultrasound (AUC = 0.945 vs. 0.917, 95% confidence interval = 0.901-0.998 vs. 0.854-0.979, using a P-value of 0.26). We then classified each nodule into new risk categories according to the output of each sample generated by the proposed method. The malignancy risks in the proposed Categories 3, 4, and 5 were 0, 18.8, and 94.5%, respectively, compared with 0, 55.1, and 88.2% using the American College of Radiology's Thyroid Imaging Reporting and Data System. Thus, this preliminary study initially indicated that the proposed method of using radiofrequency ultrasound and the ANN was more accurate at predicting malignancy and stratifying thyroid nodules than conventional ultrasound methods, thus offering significant potential to reduce the number of unnecessary thyroid biopsies.
本研究探索了结合反向散射射频超声信号和人工神经网络（ANN）技术来区分良性和恶性甲状腺结节的方法，与传统超声技术相比。该方法使用灰度共生矩阵算法和主成分分析来识别主要特征，作为 ANN 的输入。数据集由 131 个超声图像组成，其中 59 个为良性，72 个为恶性，这些结节通过随后的手术确定。结节被随机分为训练组、验证组和测试组。绘制受试者工作特征曲线（ROC）以比较 ANN 应用于射频和常规超声图像时的诊断效率。ANN 预测射频超声图像恶性的灵敏度、特异性和准确率分别为 100%、91.5%和 96.2%；从常规超声图像来看，相应的值分别为 94.4%、93.2%和 93.9%。射频超声的接收者操作特征曲线下面积（AUC）也高于常规超声（AUC=0.945 与 0.917，95%置信区间=0.901-0.998 与 0.854-0.979，使用 P 值为 0.26）。然后，我们根据所提出方法生成的每个样本的输出，将每个结节分类到新的风险类别中。与美国放射学院的甲状腺成像报告和数据系统（ACR TI-RADS）相比，建议的类别 3、4 和 5 的恶性风险分别为 0、18.8 和 94.5%。因此，这项初步研究初步表明，与传统超声方法相比，使用射频超声和 ANN 的建议方法在预测恶性和分层甲状腺结节方面更为准确，从而有可能减少不必要的甲状腺活检数量。
