Xia Jianfu, Chen Huiling, Li Qiang, Zhou Minda, Chen Limin, Cai Zhennao, Fang Yang, Zhou Hong
Department of General Surgery, The Dingli Clinical Institute of Wenzhou Medical University(Wenzhou Central Hospital), Wenzhou, Zhejiang, 325000, China.
College of Physics and Electronic Information, Wenzhou University, Wenzhou, Zhejiang, 325035, China.
Comput Methods Programs Biomed. 2017 Aug;147:37-49. doi: 10.1016/j.cmpb.2017.06.005. Epub 2017 Jun 23.
It is important to be able to accurately distinguish between benign and malignant thyroid nodules in order to make appropriate clinical decisions. The purpose of this study was to improve the effectiveness and efficiency for discriminating the malignant from benign thyroid cancers based on the Ultrasonography (US) features.
There were 114 benign nodules in 106 patients (82 women and 24 men) and 89 malignant nodules in 81 patients (69 women and 12 men) included in this study. The potential of extreme learning machine (ELM) has been explored for the first time to discriminate malignant and benign thyroid nodules based on the sonographic features in ultrasound images. The influence of two key parameters (the number of hidden neurons and type of activation function) on the performance of ELM was investigated. The relationship between feature subsets obtained by the feature selection method and the classification performance of ELM was also examined. A real-life dataset was used to evaluate the effectiveness of the proposed method in terms of classification accuracy, sensitivity, specificity, and area under the ROC (receiver operating characteristic) curve (AUC).
The results demonstrate that there are significant differences between the malignant and benign thyroid nodules (p-value<0.01), the most discriminative features are echogenicity, calcification, margin, composition and shape. Compared with other methods, the proposed method not only has achieved very promising classification accuracy via 10-fold cross-validation (CV) scheme, but also greatly reduced the computational cost compared to other counterparts. The proposed ELM-based approach achieves 87.72% ACC, 0.8672 AUC, 78.89% sensitivity, and 94.55% specificity.
Based on the empirical analysis, the proposed ELM-based approach for thyroid cancer detection has promising potential in clinical use, and it can be of assistance as an optional tool for the clinicians.
能够准确区分甲状腺良恶性结节对于做出恰当的临床决策至关重要。本研究的目的是基于超声（US）特征提高鉴别甲状腺良恶性结节的有效性和效率。
本研究纳入了106例患者（82例女性和24例男性）的114个良性结节以及81例患者（69例女性和12例男性）的89个恶性结节。首次探索了极限学习机（ELM）基于超声图像的超声特征鉴别甲状腺良恶性结节的潜力。研究了两个关键参数（隐藏神经元数量和激活函数类型）对ELM性能的影响。还检验了通过特征选择方法获得的特征子集与ELM分类性能之间的关系。使用真实数据集从分类准确率、敏感性、特异性以及ROC（受试者工作特征）曲线下面积（AUC）方面评估所提方法的有效性。
结果表明甲状腺良恶性结节之间存在显著差异（p值<0.01），最具鉴别力的特征是回声、钙化、边界、成分和形状。与其他方法相比，所提方法不仅通过10折交叉验证（CV）方案取得了非常可观的分类准确率，而且与其他同类方法相比大大降低了计算成本。所提基于ELM的方法实现了87.72%的准确率、0.8672的AUC、78.89%的敏感性和94.55%的特异性。
基于实证分析，所提基于ELM的甲状腺癌检测方法在临床应用中具有广阔的潜力，可为临床医生提供一种可选工具。
