PDCapsNet: A Convolution Neural Network Method for COVID-19 Detection from Chest X-Ray Images

Zhihao Liang, Huijuan Lu, Cunqian You, Wenjie Zhu, Li Xie, Yudong Yao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The COVID-19 epidemic started in 2019 and it is still important to develop intelligent and efficient diagnostic methods for the detection of COVID-19. In the task of COVID-19 X-ray image recognition, conventional deep neural networks encounter challenges in effectively discerning distinctive features within pneumonia images, resulting in limited generalization capability when confronted with novel samples. To address this issue, we introduce a novel model in this paper, denoted as PDCapsNet. The model effectively exploits Pyconv's multi-scale fusion technique and leverages the capsule network's capacity to encapsulate diverse attributes of specific entities within COVID-19 X-ray images, resulting in enhancements in both accuracy and generalization. Experimental results show that the proposed model outperforms other previous related works.

Original languageEnglish
Title of host publicationProceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023
Pages245-249
Number of pages5
ISBN (Electronic)9798350319156
DOIs
StatePublished - 2023
Event13th International Conference on Information Technology in Medicine and Education, ITME 2023 - Wuyishan, China
Duration: 24 Nov 202326 Nov 2023

Publication series

NameProceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023

Conference

Conference13th International Conference on Information Technology in Medicine and Education, ITME 2023
Country/TerritoryChina
CityWuyishan
Period24/11/2326/11/23

Keywords

  • Chest X-ray images
  • COVID-19
  • Deep learning
  • Image classification

Fingerprint

Dive into the research topics of 'PDCapsNet: A Convolution Neural Network Method for COVID-19 Detection from Chest X-Ray Images'. Together they form a unique fingerprint.

Cite this