Department of Radiological Technology, Tsuchiya General Hospital, Nakajima-cho 3-30, Naka-ku, Hiroshima 730-8655, Japan; Department of Diagnostic Radiology, Graduate School of Biomedical Sciences, Hiroshima University, Hiroshima, Japan.
Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1 Honjo, Kumamoto 860-8556, Japan.
Radiography (Lond). 2021 Aug;27(3):920-926. doi: 10.1016/j.radi.2021.03.001. Epub 2021 Mar 21.
We compared the diagnostic performance of morphological methods such as the major axis, the minor axis, the volume and sphericity and of machine learning with texture analysis in the identification of lymph node metastasis in patients with thyroid cancer who had undergone contrast-enhanced CT studies.
We sampled 772 lymph nodes with histology defined tissue types (84 metastatic and 688 benign lymph nodes) that were visualised on CT images of 117 patients. A support vector machine (SVM), free programming software (Python), and the scikit-learn machine learning library were used to discriminate metastatic-from benign lymph nodes. We assessed 96 texture and 4 morphological features (major axis, minor axis, volume, sphericity) that were reported useful for the differentiation between metastatic and benign lymph nodes on CT images. The area under the curve (AUC) obtained by receiver operating characteristic analysis of univariate logistic regression and SVM classifiers were calculated for the training and testing datasets.
The AUC for all classifiers in training and testing datasets was 0.96 and 0.86, at the SVM for machine learning. When we applied conventional methods to the training and testing datasets, the AUCs were 0.63 and 0.48 for the major axis, 0.70 and 0.44 for the minor axis, 0.66 and 0.43 for the volume, and 0.69 and 0.54 for sphericity, respectively. The SVM using texture features yielded significantly higher AUCs than univariate logistic regression models using morphological features (p = 0.001).
For the identification of metastatic lymph nodes from thyroid cancer on contrast-enhanced CT images, machine learning combined with texture analysis was superior to conventional diagnostic methods with the morphological parameters.
Our findings suggest that in patients with thyroid cancer and suspected lymph node metastasis who undergo contrast-enhanced CT studies, machine learning using texture analysis is high diagnostic value for the identification of metastatic lymph nodes.
我们比较了形态学方法（如长轴、短轴、体积和球形度）和机器学习与纹理分析在鉴别甲状腺癌患者增强 CT 检查中淋巴结转移的诊断性能。
我们对 117 名患者 CT 图像上可见的 772 个具有组织学定义的淋巴结（84 个转移性和 688 个良性淋巴结）进行了采样。使用支持向量机（SVM）、免费编程软件（Python）和 scikit-learn 机器学习库来区分转移性和良性淋巴结。我们评估了 96 个纹理和 4 个形态特征（长轴、短轴、体积、球形度），这些特征在 CT 图像上被报道有助于区分转移性和良性淋巴结。通过单变量逻辑回归和 SVM 分类器的接收者操作特征分析获得的曲线下面积（AUC）用于训练和测试数据集。
在训练和测试数据集中，所有分类器的 AUC 均为 0.96 和 0.86，在机器学习中为 SVM。当我们将传统方法应用于训练和测试数据集时，长轴的 AUC 分别为 0.63 和 0.48，短轴为 0.70 和 0.44，体积为 0.66 和 0.43，球形度为 0.69 和 0.54。使用纹理特征的 SVM 产生的 AUC 明显高于使用形态特征的单变量逻辑回归模型（p=0.001）。
对于增强 CT 图像上甲状腺癌转移性淋巴结的识别，使用纹理分析的机器学习优于传统的形态学参数诊断方法。
我们的发现表明，在接受增强 CT 检查的甲状腺癌伴可疑淋巴结转移的患者中，使用纹理分析的机器学习对识别转移性淋巴结具有很高的诊断价值。
