中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中国科学院分子影像重点实验室
Online Transfer Learning for Differential Diagnosis of Benign and Malignant Thyroid Nodules With Ultrasound Images

文献类型：期刊论文

作者Zhou, Hui1,2; Wang, Kun1,2; Tian, Jie1,2,3
刊名IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
出版日期2020-10-01
卷号67期号:10页码:2773-2780
ISSN号0018-9294
关键词Cancer Biological system modeling Ultrasonic imaging Feature extraction Radiomics Training Deep learning Diagnosis online learning radiomics transfer learning thyroid nodules ultrasound images
DOI10.1109/TBME.2020.2971065
通讯作者Tian, Jie(jie.tian@ia.ac.cn)
英文摘要Objective: We aimed to propose a highly automatic and objective model named online transfer learning (OTL) for the differential diagnosis of benign and malignant thyroid nodules from ultrasound (US) images. Methods: The OTL mothed combined the strategy of transfer learning and online learning. Two datasets (1750 thyroid nodules with 1078 benign and 672 malignant nodules, and 3852 thyroid nodules with 3213 benign and 639 malignant nodules) were collected to develop the model. The diagnostic accuracy was also compared with VGG-16 based transfer learning model and different input images based model. Analysis of receiver operating characteristic (ROC) curves were performed to calculate optimal area under it (AUC) for benign and malignant nodules. Results: AUC, sensitivity and specificity of OTL were 0.98 (95% confidence interval [CI]: 0.97-0.99), 98.7% (95% confidence interval [CI]: 97.8%-99.6%) and 98.8% (95% confidence interval [CI]: 97.9%-99.7%) in the final online learning step, which was significantly better than other deep learning models (P < 0.01). Conclusion: OTL model shows the best overall performance comparing with other deep learning models. The model holds a good potential for improving the overall diagnostic efficacy in thyroid nodule US examinations. Significance: The proposed OTL model could be seamlessly integrated into the conventional work-flow of thyroid nodule US examinations.
WOS关键词FEATURES ; RISK ; US ; CLASSIFICATION ; MANAGEMENT ; CARCINOMA ; CANCER
资助项目Ministry of Science and Technology of China[2017YFA0205200] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81527805] ; National Natural Science Foundation of China[61671449] ; Chinese Academy of Sciences[GJJSTD20170004] ; Chinese Academy of Sciences[KFJ-STS-ZDTP-059] ; Chinese Academy of Sciences[81930053] ; Chinese Academy of Sciences[YJKYYQ2018 0048] ; Chinese Academy of Sciences[XDB32030200]
WOS研究方向Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000571741600007
资助机构Ministry of Science and Technology of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/42006]  
专题自动化研究所_中国科学院分子影像重点实验室
通讯作者Tian, Jie
作者单位1.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.Beijing Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhou, Hui,Wang, Kun,Tian, Jie. Online Transfer Learning for Differential Diagnosis of Benign and Malignant Thyroid Nodules With Ultrasound Images[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,2020,67(10):2773-2780.
APA Zhou, Hui,Wang, Kun,&Tian, Jie.(2020).Online Transfer Learning for Differential Diagnosis of Benign and Malignant Thyroid Nodules With Ultrasound Images.IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,67(10),2773-2780.
MLA Zhou, Hui,et al."Online Transfer Learning for Differential Diagnosis of Benign and Malignant Thyroid Nodules With Ultrasound Images".IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 67.10(2020):2773-2780.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。