Automatic diagnosis of COPD in lung CT images based on multi-view DCNN
Automatic diagnosis of COPD in lung CT images based on multi-view DCNN
Chronic obstructive pulmonary disease (COPD) has long been one of the leading causes of morbidity and mortality worldwide. Numerous studies have shown that CT image analysis is an effective way to diagnose patients with COPD. Automatic diagnosis of CT images using computer vision will shorten the time a patient takes to confirm COPD. This enables patients to receive timely treatment. CT images are three-dimensional data. The extraction of 3D texture features is the core of classification problem. However, the classification accuracy of the current computer vision models is still not high when extracting these features. Therefore, computer vision assisted diagnosis has not been widely used. In this paper, we proposed MV-DCNN, a multi-view deep neural network based on 15 directions. The experimental results show that compared with the state-of-art methods, this method significantly improves the accuracy of COPD classification, with an accuracy of 97.7%. The model proposed here can be used in the medical institutions for diagnosis of COPD.
COPD, Classification, Deep convolutional neural network, Multi-view
571-578
Bao, Yin
d23b032b-5ea1-4610-b1fe-77f5eb4cd559
Al Makady, Yasseen Hamad
8125c167-d6ef-45bf-ac22-b9a7e72d36fd
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
di Baja, Gabriella Sanniti
4 February 2021
Bao, Yin
d23b032b-5ea1-4610-b1fe-77f5eb4cd559
Al Makady, Yasseen Hamad
8125c167-d6ef-45bf-ac22-b9a7e72d36fd
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
di Baja, Gabriella Sanniti
Bao, Yin, Al Makady, Yasseen Hamad and Mahmoodi, Sasan
(2021)
Automatic diagnosis of COPD in lung CT images based on multi-view DCNN.
De Marsico, Maria, di Baja, Gabriella Sanniti and Fred, Ana
(eds.)
In ICPRAM 2021 - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods.
SciTePress.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Chronic obstructive pulmonary disease (COPD) has long been one of the leading causes of morbidity and mortality worldwide. Numerous studies have shown that CT image analysis is an effective way to diagnose patients with COPD. Automatic diagnosis of CT images using computer vision will shorten the time a patient takes to confirm COPD. This enables patients to receive timely treatment. CT images are three-dimensional data. The extraction of 3D texture features is the core of classification problem. However, the classification accuracy of the current computer vision models is still not high when extracting these features. Therefore, computer vision assisted diagnosis has not been widely used. In this paper, we proposed MV-DCNN, a multi-view deep neural network based on 15 directions. The experimental results show that compared with the state-of-art methods, this method significantly improves the accuracy of COPD classification, with an accuracy of 97.7%. The model proposed here can be used in the medical institutions for diagnosis of COPD.
Text
PaperDCNN
- Accepted Manuscript
More information
Published date: 4 February 2021
Additional Information:
Publisher Copyright:
© 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved
Keywords:
COPD, Classification, Deep convolutional neural network, Multi-view
Identifiers
Local EPrints ID: 445469
URI: http://eprints.soton.ac.uk/id/eprint/445469
PURE UUID: d5977c9b-b294-4d03-a584-caafb3be8f1c
Catalogue record
Date deposited: 10 Dec 2020 17:31
Last modified: 17 Mar 2024 06:09
Export record
Contributors
Author:
Yin Bao
Author:
Yasseen Hamad Al Makady
Author:
Sasan Mahmoodi
Editor:
Maria De Marsico
Editor:
Gabriella Sanniti di Baja
Editor:
Ana Fred
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics