Research progress on computed tomography image detection and classification of pulmonary nodule based on deep learning.
10.7507/1001-5515.201806019
- Author:
Jingxuan WANG
1
;
Lan LIN
2
;
Siyuan ZHAO
3
;
Xuetao WU
1
;
Shuicai WU
1
Author Information
1. College of Life Science and Bio-engineering, Beijing University of Technology, Beijing 100124, P.R.China.
2. College of Life Science and Bio-engineering, Beijing University of Technology, Beijing 100124, P.R.China.lanlin@bjut.edu.cn.
3. College of software engineering, Beijing University of Technology, Beijing 100124, P.R.China.
- Publication Type:Journal Article
- Keywords:
classification;
deep learning;
detection;
pulmonary nodules
- MeSH:
Deep Learning;
Humans;
Lung Neoplasms;
diagnostic imaging;
Radiographic Image Interpretation, Computer-Assisted;
Reproducibility of Results;
Solitary Pulmonary Nodule;
diagnostic imaging;
Tomography, X-Ray Computed
- From:
Journal of Biomedical Engineering
2019;36(4):670-676
- CountryChina
- Language:Chinese
-
Abstract:
Computer-aided diagnosis based on computed tomography (CT) image can realize the detection and classification of pulmonary nodules, and improve the survival rate of early lung cancer, which has important clinical significance. In recent years, with the rapid development of medical big data and artificial intelligence technology, the auxiliary diagnosis of lung cancer based on deep learning has gradually become one of the most active research directions in this field. In order to promote the deep learning in the detection and classification of pulmonary nodules, we reviewed the research progress in this field based on the relevant literatures published at domestic and overseas in recent years. This paper begins with a brief introduction of two widely used lung CT image databases: lung image database consortium and image database resource initiative (LIDC-IDRI) and Data Science Bowl 2017. Then, the detection and classification of pulmonary nodules based on different network structures are introduced in detail. Finally, some problems of deep learning in lung CT image nodule detection and classification are discussed and conclusions are given. The development prospect is also forecasted, which provides reference for future application research in this field.
