Your browser doesn't support javascript.
NIA-Network: Towards improving lung CT infection detection for COVID-19 diagnosis.
Li, Wei; Chen, Jinlin; Chen, Ping; Yu, Lequan; Cui, Xiaohui; Li, Yiwei; Cheng, Fang; Ouyang, Wen.
  • Li W; School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, PR China; Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi, Jiangsu, PR China; Science Center for Future Foods, Jiangnan University, Wuxi, Jiangsu, PR China.
  • Chen J; Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China.
  • Chen P; Department of Engineering, University of Massachusetts, Boston, USA. Electronic address: Ping.Chen@umb.edu.
  • Yu L; Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong, China.
  • Cui X; School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, PR China.
  • Li Y; School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, PR China.
  • Cheng F; Department of Cancer Center, Union Hospital of Tongji Medical College of Huazhong University of Science and Technology, Wuhan, PR China.
  • Ouyang W; Department of Radiation and Medical Oncology, Zhongnan Hospital, Wuhan University, Wuhan, PR China.
Artif Intell Med ; 117: 102082, 2021 07.
Article in English | MEDLINE | ID: covidwho-1213041
ABSTRACT
During pandemics (e.g., COVID-19) physicians have to focus on diagnosing and treating patients, which often results in that only a limited amount of labeled CT images is available. Although recent semi-supervised learning algorithms may alleviate the problem of annotation scarcity, limited real-world CT images still cause those algorithms producing inaccurate detection results, especially in real-world COVID-19 cases. Existing models often cannot detect the small infected regions in COVID-19 CT images, such a challenge implicitly causes that many patients with minor symptoms are misdiagnosed and develop more severe symptoms, causing a higher mortality. In this paper, we propose a new method to address this challenge. Not only can we detect severe cases, but also detect minor symptoms using real-world COVID-19 CT images in which the source domain only includes limited labeled CT images but the target domain has a lot of unlabeled CT images. Specifically, we adopt Network-in-Network and Instance Normalization to build a new module (we term it NI module) and extract discriminative representations from CT images from both source and target domains. A domain classifier is utilized to implement infected region adaptation from source domain to target domain in an Adversarial Learning manner, and learns domain-invariant region proposal network (RPN) in the Faster R-CNN model. We call our model NIA-Network (Network-in-Network, Instance Normalization and Adversarial Learning), and conduct extensive experiments on two COVID-19 datasets to validate our approach. The experimental results show that our model can effectively detect infected regions with different sizes and achieve the highest diagnostic accuracy compared with existing SOTA methods.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Machine Learning / COVID-19 / Lung Type of study: Diagnostic study / Prognostic study Limits: Humans Language: English Journal: Artif Intell Med Journal subject: Medical Informatics Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Machine Learning / COVID-19 / Lung Type of study: Diagnostic study / Prognostic study Limits: Humans Language: English Journal: Artif Intell Med Journal subject: Medical Informatics Year: 2021 Document Type: Article