Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification

Malaria is a lethal disease responsible for thousands of deaths worldwide every year. Manual methods of malaria diagnosis are timeconsuming that require a great deal of human expertise and efforts. Computerbased automated diagnosis of diseases is progressively becoming popular. Although deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Amin, I., Hassan, S., Belhaouari, S.B., Azam, M.H.
Format: Article
Published: 2023
Online Access:http://scholars.utp.edu.my/id/eprint/34294/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85145346928&doi=10.32604%2fcmc.2023.033860&partnerID=40&md5=5af709176d85f55aca1e201e3a3d4382
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknologi Petronas
id oai:scholars.utp.edu.my:34294
record_format eprints
spelling oai:scholars.utp.edu.my:342942023-01-17T13:35:51Z http://scholars.utp.edu.my/id/eprint/34294/ Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification Amin, I. Hassan, S. Belhaouari, S.B. Azam, M.H. Malaria is a lethal disease responsible for thousands of deaths worldwide every year. Manual methods of malaria diagnosis are timeconsuming that require a great deal of human expertise and efforts. Computerbased automated diagnosis of diseases is progressively becoming popular. Although deep learning models show high performance in the medical field, it demands a large volume of data for training which is hard to acquire for medical problems. Similarly, labeling of medical images can be done with the help of medical experts only. Several recent studies have utilized deep learning models to develop efficient malaria diagnostic system, which showed promising results. However, the most common problem with these models is that they need a large amount of data for training. This paper presents a computer-aided malaria diagnosis system that combines a semi-supervised generative adversarial network and transfer learning. The proposed model is trained in a semi-supervised manner and requires less training data than conventional deep learning models. Performance of the proposed model is evaluated on a publicly available dataset of blood smear images (with malariainfected and normal class) and achieved a classification accuracy of 96.6. © 2023 Tech Science Press. All rights reserved. 2023 Article NonPeerReviewed Amin, I. and Hassan, S. and Belhaouari, S.B. and Azam, M.H. (2023) Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification. Computers, Materials and Continua, 74 (3). pp. 6335-6349. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85145346928&doi=10.32604%2fcmc.2023.033860&partnerID=40&md5=5af709176d85f55aca1e201e3a3d4382 10.32604/cmc.2023.033860 10.32604/cmc.2023.033860 10.32604/cmc.2023.033860
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Malaria is a lethal disease responsible for thousands of deaths worldwide every year. Manual methods of malaria diagnosis are timeconsuming that require a great deal of human expertise and efforts. Computerbased automated diagnosis of diseases is progressively becoming popular. Although deep learning models show high performance in the medical field, it demands a large volume of data for training which is hard to acquire for medical problems. Similarly, labeling of medical images can be done with the help of medical experts only. Several recent studies have utilized deep learning models to develop efficient malaria diagnostic system, which showed promising results. However, the most common problem with these models is that they need a large amount of data for training. This paper presents a computer-aided malaria diagnosis system that combines a semi-supervised generative adversarial network and transfer learning. The proposed model is trained in a semi-supervised manner and requires less training data than conventional deep learning models. Performance of the proposed model is evaluated on a publicly available dataset of blood smear images (with malariainfected and normal class) and achieved a classification accuracy of 96.6. © 2023 Tech Science Press. All rights reserved.
format Article
author Amin, I.
Hassan, S.
Belhaouari, S.B.
Azam, M.H.
spellingShingle Amin, I.
Hassan, S.
Belhaouari, S.B.
Azam, M.H.
Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
author_facet Amin, I.
Hassan, S.
Belhaouari, S.B.
Azam, M.H.
author_sort Amin, I.
title Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
title_short Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
title_full Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
title_fullStr Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
title_full_unstemmed Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification
title_sort transfer learning-based semi-supervised generative adversarial network for malaria classification
publishDate 2023
url http://scholars.utp.edu.my/id/eprint/34294/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85145346928&doi=10.32604%2fcmc.2023.033860&partnerID=40&md5=5af709176d85f55aca1e201e3a3d4382
_version_ 1756062140458860544