模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2023, Vol. 36 Issue (6): 544-555    DOI: 10.16451/j.cnki.issn1003-6059.202306005
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Pneumonia Classification and Recognition Method Based on Multi-resolution Attention Dense Network
ZHOU Tao1,2, YE Xinyu1,2, LU Huiling3, CHANG Xiaoyu1,2, LIU Yuncan1,2
1. Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission, North Minzu University, Yinchuan 750021;
2. Department of Computer Science and Engineering, North Minzu University, Yinchuan 750021;
3. Department of Science, Ningxia Medical University, Yinchuan 750004

Download: PDF (2626 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  X-ray film of pneumonia suffers from inconspicuous imaging features, low contrast between lesions and surrounding tissues, and blurred edges. Therefore, a pneumonia classification and recognition method based on multi-resolution attention dense network is proposed. Shallow localization information and deep semantic information are deeply fused. A multi-resolution spatial attention gate is constructed to enhance semantic interaction between deep and shallow information at different resolutions, establishing interdependency for lesion information in deep and shallow information. In addition, the coordinate frequency attention is designed to adaptively enhance the representation of pneumonia features in a complementary manner of orientation and location. Experiments on five pneumonia X-ray datasets including ChestXRay2017 show that the proposed method achieves better performance in pneumonia classification and recognition task with robustness on the public pneumonia dataset.
Key wordsPneumonia Recognition      Multi-resolution Dense Connection      Spatial Attention Gate      Coordinate Frequency Attention     
Received: 04 April 2023     
ZTFLH: TP181  
Fund:National Natural Science Foundation of China(No.62062003), Ningxia Natural Science Foundation Project(No.2022AAC03149), Key Research and Development Project of Ningxia Autonomous Region(No.2020BEB04022)
Corresponding Authors: ZHOU Tao, Ph.D., professor. His research interests include medical image processing, deep learning and pattern recognition.   
About author:: About Author:YE Xinyu, master student. His research interests include medical image processing and computer-aided diagnosis.LU Huiling, master, associate professor. Her research inte-rests include image processing.CHANG Xiaoyu, master student. Her research interests include medical image processing.LIU Yuncan, master student. Her research interests include medical image processing.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHOU Tao
YE Xinyu
LU Huiling
CHANG Xiaoyu
LIU Yuncan
Cite this article:   
ZHOU Tao,YE Xinyu,LU Huiling等. Pneumonia Classification and Recognition Method Based on Multi-resolution Attention Dense Network[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(6): 544-555.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202306005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2023/V36/I6/544
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn