Hongxun Wu1, Zhaohong Deng2, Bingjie Zhang1, Qianyun Liu1, Junyong Chen2. 1. 1 Department of Ultrasound, Jiangyuan Hospital Affiliated to Jiangsu Institute of Nuclear Medicine (Key Laboratory of Nuclear Medicine, Ministry of Health/Jiangsu Key Laboratory of Molecular Nuclear Medicine), 20 Qianrong Rd, Wuxi, Jiangsu 214063, China. 2. 2 School of Digital Media, Jiangnan University, Wuxi, Jiangsu, China.
Abstract
OBJECTIVE: The purpose of this article is to construct classifier models using machine learning algorithms and to evaluate their diagnostic performances for differentiating malignant from benign thyroid nodules. MATERIALS AND METHODS: This study included 970 histopathologically proven thyroid nodules in 970 patients. Two radiologists retrospectively reviewed ultrasound images, and nodules were graded according to a five-tier sonographic scoring system. Statistically significant variables based on an experienced radiologist's observations were obtained with attribute optimization using fivefold cross-validation and applied as the input nodes to build models for predicting malignancy of nodules. The performances of the machine learning algorithms and radiologists were compared using ROC curve analysis. RESULTS: Diagnosis by the experienced radiologist achieved the highest predictive accuracy of 88.66% with a specificity of 85.33%, whereas the radial basis function (RBF)-neural network (NN) achieved the highest sensitivity of 92.31%. The AUC value for diagnosis by the experienced radiologist (AUC = 0.9135) was greater than those for diagnosis by the less experienced radiologist, the naïve Bayes classifier, the support vector machine, and the RBF-NN (AUC = 0.8492, 0.8811, 0.9033, and 0.9103, respectively; p < 0.05). CONCLUSION: The machine learning algorithms underperformed with respect to the experienced radiologist's readings used to construct them, and the RBF-NN outperformed the other machine learning algorithm models.
OBJECTIVE: The purpose of this article is to construct classifier models using machine learning algorithms and to evaluate their diagnostic performances for differentiating malignant from benign thyroid nodules. MATERIALS AND METHODS: This study included 970 histopathologically proven thyroid nodules in 970 patients. Two radiologists retrospectively reviewed ultrasound images, and nodules were graded according to a five-tier sonographic scoring system. Statistically significant variables based on an experienced radiologist's observations were obtained with attribute optimization using fivefold cross-validation and applied as the input nodes to build models for predicting malignancy of nodules. The performances of the machine learning algorithms and radiologists were compared using ROC curve analysis. RESULTS: Diagnosis by the experienced radiologist achieved the highest predictive accuracy of 88.66% with a specificity of 85.33%, whereas the radial basis function (RBF)-neural network (NN) achieved the highest sensitivity of 92.31%. The AUC value for diagnosis by the experienced radiologist (AUC = 0.9135) was greater than those for diagnosis by the less experienced radiologist, the naïve Bayes classifier, the support vector machine, and the RBF-NN (AUC = 0.8492, 0.8811, 0.9033, and 0.9103, respectively; p < 0.05). CONCLUSION: The machine learning algorithms underperformed with respect to the experienced radiologist's readings used to construct them, and the RBF-NN outperformed the other machine learning algorithm models.
Authors: Kelly Daniels; Sriharsha Gummadi; Ziyin Zhu; Shuo Wang; Jena Patel; Brian Swendseid; Andrej Lyshchik; Joseph Curry; Elizabeth Cottrill; John Eisenbrey Journal: JAMA Otolaryngol Head Neck Surg Date: 2020-01-01 Impact factor: 6.223
Authors: Hailong Li; Lili He; Jonathan A Dudley; Thomas C Maloney; Elanchezhian Somasundaram; Samuel L Brady; Nehal A Parikh; Jonathan R Dillman Journal: Pediatr Radiol Date: 2020-10-13
Authors: Jeong-Kweon Seo; Young Jae Kim; Kwang Gi Kim; Ilah Shin; Jung Hee Shin; Jin Young Kwak Journal: Biomed Res Int Date: 2017-12-19 Impact factor: 3.411