2019 Novel Coronavirus-Infected Pneumonia on CT: A Feasibility Study of Few-Shot Learning for Computerized Diagnosis of Emergency Diseases

被引:8
作者
Lai, Yaoming [1 ]
Li, Guangming [2 ]
Wu, Dongmei [3 ]
Lian, Wanmin [4 ]
Li, Cheng [4 ]
Tian, Junzhang [4 ]
Ma, Xiaofen [4 ]
Chen, Hui [2 ]
Xu, Wen [2 ]
Wei, Jun [1 ]
Zhang, Yaqin [5 ]
Jiang, Guihua [4 ]
机构
[1] Guangzhou Percept Vis Med Technol Inc, Guangzhou 510000, Peoples R China
[2] Hubei Univ Arts & Sci, Affiliated Hosp, Xiangyang Cent Hosp, Xiangyang 441000, Peoples R China
[3] Nanxishan Hosp Guangxi Zhuang Autonomous Reg, Guilin 541000, Peoples R China
[4] Guangdong Second Prov Gen Hosp, Dept Med Imaging, Guangzhou 510000, Peoples R China
[5] Sun Yat Sen Univ, Affiliated Hosp 5, Dept Radiol, Zhuhai 519000, Peoples R China
来源
IEEE ACCESS | 2020年 / 8卷 / 08期
基金
中国国家自然科学基金;
关键词
Lung; COVID-19; Training; Lesions; Hospitals; Computed tomography; chest CT; 2019 novel coronavirus-infected pneumonia; few-shot learning; CLINICAL CHARACTERISTICS;
D O I
10.1109/ACCESS.2020.3033069
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
COVID-19 is an emerging disease with transmissibility and severity. So far, there are no effective therapeutic drugs or vaccines for COVID-19. The most serious complication of COVID-19 is a type of pneumonia called 2019 novel coronavirus-infected pneumonia (NCIP) with about 4.3% mortality rate. Comparing to chest Digital Radiography (DR), it is recently reported that chest Computed Tomography (CT) is more useful to serve as the early screening and diagnosis tool for NCIP. In this study, aimed to help physicians make the diagnostic decision, we develop a machine learning (ML) approach for automated diagnosis of NCIP on chest CT. Different from most ML approaches which often require training on thousands or millions of samples, we design a few-shot learning approach, in which we combine few-shot learning with weakly supervised model training, for computerized NCIP diagnosis. A total of 824 patients are retrospectively collected from two Hospitals with IRB approval. We first use 9 patients with clinically confirmed NCIP and 20 patients without known lung diseases for training a location detector which is a multitask deep convolutional neural network (DCNN) designed to output a probability of NCIP and the segmentation of targeted lesion area. An experienced radiologist manually localizes the potential locations of NCIPs on chest CTs of 9 COVID-19 patients and interactively segments the area of the NCIP lesions as the reference standard. Then, the multitask DCNN is furtherly fine-tuned by a weakly supervised learning scheme with 291 case-level labeled samples without lesion labels. A test set of 293 patients is independently collected for evaluation. With our NCIP-Net, the test AUC is 0.91. Our system has potential to serve as the NCIP screening and diagnosis tools for the fight of COVID-19S endemic and pandemic.
引用
收藏
页码:194158 / 194165
页数:8
相关论文
共 15 条
[1]   Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases [J].
Ai, Tao ;
Yang, Zhenlu ;
Hou, Hongyan ;
Zhan, Chenao ;
Chen, Chong ;
Lv, Wenzhi ;
Tao, Qian ;
Sun, Ziyong ;
Xia, Liming .
RADIOLOGY, 2020, 296 (02) :E32-E40
[2]  
[Anonymous], 2017, P IEEE INT C COMPUTE
[3]   A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster [J].
Chan, Jasper Fuk-Woo ;
Yuan, Shuofeng ;
Kok, Kin-Hang ;
To, Kelvin Kai-Wang ;
Chu, Hin ;
Yang, Jin ;
Xing, Fanfan ;
Liu, Jieling ;
Yip, Cyril Chik-Yan ;
Poon, Rosana Wing-Shan ;
Tsoi, Hoi-Wah ;
Lo, Simon Kam-Fai ;
Chan, Kwok-Hung ;
Poon, Vincent Kwok-Man ;
Chan, Wan-Mui ;
Ip, Jonathan Daniel ;
Cai, Jian-Piao ;
Cheng, Vincent Chi-Chung ;
Chen, Honglin ;
Hui, Christopher Kim-Ming ;
Yuen, Kwok-Yung .
LANCET, 2020, 395 (10223) :514-523
[4]   Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study [J].
Chen, Nanshan ;
Zhou, Min ;
Dong, Xuan ;
Qu, Jieming ;
Gong, Fengyun ;
Han, Yang ;
Qiu, Yang ;
Wang, Jingli ;
Liu, Ying ;
Wei, Yuan ;
Xia, Jia'an ;
Yu, Ting ;
Zhang, Xinxin ;
Zhang, Li .
LANCET, 2020, 395 (10223) :507-513
[5]   AutoAugment: Learning Augmentation Strategies from Data [J].
Cubuk, Ekin D. ;
Zoph, Barret ;
Mane, Dandelion ;
Vasudevan, Vijay ;
Le, Quoc V. .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :113-123
[6]  
Gu YC, 2019, I S BIOMED IMAGING, P438, DOI [10.1109/ISBI.2019.8759207, 10.1109/isbi.2019.8759207]
[7]   Clinical Characteristics of Coronavirus Disease 2019 in China [J].
Guan, W. ;
Ni, Z. ;
Hu, Yu ;
Liang, W. ;
Ou, C. ;
He, J. ;
Liu, L. ;
Shan, H. ;
Lei, C. ;
Hui, D. S. C. ;
Du, B. ;
Li, L. ;
Zeng, G. ;
Yuen, K. -Y. ;
Chen, R. ;
Tang, C. ;
Wang, T. ;
Chen, P. ;
Xiang, J. ;
Li, S. ;
Wang, Jin-lin ;
Liang, Z. ;
Peng, Y. ;
Wei, L. ;
Liu, Y. ;
Hu, Ya-hua ;
Peng, P. ;
Wang, Jian-ming ;
Liu, J. ;
Chen, Z. ;
Li, G. ;
Zheng, Z. ;
Qiu, S. ;
Luo, J. ;
Ye, C. ;
Zhu, S. ;
Zhong, N. .
NEW ENGLAND JOURNAL OF MEDICINE, 2020, 382 (18) :1708-1720
[8]   Coronavirus (COVID-19) Outbreak: What the Department of Radiology Should Know [J].
Kooraki, Soheil ;
Hosseiny, Melina ;
Myers, Lee ;
Gholamrezanezhad, Ali .
JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY, 2020, 17 (04) :447-451
[9]   One-shot learning of object categories [J].
Li, FF ;
Fergus, R ;
Perona, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (04) :594-611
[10]   U-Net: Convolutional Networks for Biomedical Image Segmentation [J].
Ronneberger, Olaf ;
Fischer, Philipp ;
Brox, Thomas .
MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 :234-241