Machine Learning-Assisted System for Thyroid Nodule Diagnosis

doi:10.1089/thy.2018.0380

	Machine Learning-Assisted System for Thyroid Nodule Diagnosis
	Zhang, Bin 1; Tian, Jie 3; Pei, Shufang 4; Chen, Yubing 2; He, Xin 6; Dong, Yuhao 5; Zhang, Lu 5; Mo, Xiaokai 5; Huang, Wenhui 5; Cong, Shuzhen 4
刊名	THYROID
	2019-04-27
页码	10
关键词	thyroid nodule ultrasound machine learning random forest diagnosis
ISSN号	1050-7256
DOI	10.1089/thy.2018.0380
通讯作者	Zhang, Shuixing(shui7515@126.com)
英文摘要	Background: Ultrasound (US) examination is helpful in the differential diagnosis of thyroid nodules (malignant vs. benign), but its accuracy relies heavily on examiner experience. Therefore, the aim of this study was to develop a less subjective diagnostic model aided by machine learning. Methods: A total of 2064 thyroid nodules (2032 patients, 695 male; M-age = 45.25 +/- 13.49 years) met all of the following inclusion criteria: (i) hemi- or total thyroidectomy, (ii) maximum nodule diameter 2.5 cm, (iii) examination by conventional US and real-time elastography within one month before surgery, and (iv) no previous thyroid surgery or percutaneous thermotherapy. Models were developed using 60% of randomly selected samples based on nine commonly used algorithms, and validated using the remaining 40% of cases. All models function with a validation data set that has a pretest probability of malignancy of 10%. The models were refined with machine learning that consisted of 1000 repetitions of derivatization and validation, and compared to diagnosis by an experienced radiologist. Sensitivity, specificity, accuracy, and area under the curve (AUC) were calculated. Results: A random forest algorithm led to the best diagnostic model, which performed better than radiologist diagnosis based on conventional US only (AUC = 0.924 [confidence interval (CI) 0.895-0.953] vs. 0.834 [CI 0.815-0.853]) and based on both conventional US and real-time elastography (AUC = 0.938 [CI 0.914-0.961] vs. 0.843 [CI 0.829-0.857]). Conclusions: Machine-learning algorithms based on US examinations, particularly the random forest classifier, may diagnose malignant thyroid nodules better than radiologists.
资助项目	National Scientific Foundation of China[81571664] ; National Scientific Foundation of China[81871323] ; National Scientific Foundation of China[81801665] ; Science and Technology Planning Project of Guangdong Province[2014A020212244] ; Science and Technology Planning Project of Guangdong Province[2016A020216020] ; Scientific Research General Project of Guangzhou Science Technology and Innovation Commission[201605110912158] ; China Postdoctoral Science Foundation[2016M600145] ; Guangdong Grand Science and Technology Special Project[2015B010106008]
WOS关键词	SHEAR-WAVE ELASTOGRAPHY ; FINE-NEEDLE-ASPIRATION ; REAL-TIME ELASTOGRAPHY ; DIFFERENTIAL-DIAGNOSIS ; ULTRASOUND ELASTOGRAPHY ; MANAGEMENT ; BENIGN ; US ; PERFORMANCE ; ACCURACY
WOS研究方向	Endocrinology & Metabolism
语种	英语
出版者	MARY ANN LIEBERT, INC
WOS记录号	WOS:000466533800001
资助机构	National Scientific Foundation of China ; Science and Technology Planning Project of Guangdong Province ; Scientific Research General Project of Guangzhou Science Technology and Innovation Commission ; China Postdoctoral Science Foundation ; Guangdong Grand Science and Technology Special Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24908]
专题	中国科学院自动化研究所
通讯作者	Zhang, Shuixing
作者单位	1.Jinan Univ, Affiliated Hosp 1, Dept Radiol, Guangzhou, Guangdong, Peoples R China 2.Jinan Univ, Affiliated Hosp 1, Informat Ctr, Guangzhou, Guangdong, Peoples R China 3.Chinese Acad Sci, Key Lab Mol Imaging, Beijing, Peoples R China 4.Acad Med Sci, Guangdong Prov Peoples Hosp, Dept Ultrasound, Guangzhou, Guangdong, Peoples R China 5.Acad Med Sci, Guangdong Prov Peoples Hosp, Dept Radiol, Guangzhou, Guangdong, Peoples R China 6.Shanghai Univ Finance & Econ, Sch Stat & Management, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Bin,Tian, Jie,Pei, Shufang,et al. Machine Learning-Assisted System for Thyroid Nodule Diagnosis[J]. THYROID,2019:10.
APA	Zhang, Bin.,Tian, Jie.,Pei, Shufang.,Chen, Yubing.,He, Xin.,...&Zhang, Shuixing.(2019).Machine Learning-Assisted System for Thyroid Nodule Diagnosis.THYROID,10.
MLA	Zhang, Bin,et al."Machine Learning-Assisted System for Thyroid Nodule Diagnosis".THYROID (2019):10.