Enhancing Small Medical Dataset Classification Performance Using GAN
Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/10/1/28 |
| _version_ | 1797611083157995520 |
|---|---|
| author | Mohammad Alauthman Ahmad Al-qerem Bilal Sowan Ayoub Alsarhan Mohammed Eshtay Amjad Aldweesh Nauman Aslam |
| author_facet | Mohammad Alauthman Ahmad Al-qerem Bilal Sowan Ayoub Alsarhan Mohammed Eshtay Amjad Aldweesh Nauman Aslam |
| author_sort | Mohammad Alauthman |
| collection | DOAJ |
| description | Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field. |
| first_indexed | 2024-03-11T06:23:51Z |
| format | Article |
| id | doaj.art-3850ca5d28894d5a91a73c4fb9a06d9c |
| institution | Directory Open Access Journal |
| issn | 2227-9709 |
| language | English |
| last_indexed | 2024-03-11T06:23:51Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj.art-3850ca5d28894d5a91a73c4fb9a06d9c2023-11-17T11:43:35ZengMDPI AGInformatics2227-97092023-03-011012810.3390/informatics10010028Enhancing Small Medical Dataset Classification Performance Using GANMohammad Alauthman0Ahmad Al-qerem1Bilal Sowan2Ayoub Alsarhan3Mohammed Eshtay4Amjad Aldweesh5Nauman Aslam6Department of Information Security, Faculty of Information Technology, University of Petra, Amman 11196, JordanComputer Science Department, Faculty of Information Technology, Zarqa University, Zarqa 13110, JordanDepartment of Business Intelligence and Data Analytics, University of Petra, Amman 11196, JordanDepartment of Information Technology, Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology, The Hashemite University, Zarqa 13133, JordanAbdul Aziz Al Ghurair School of Advanced Computing (ASAC), Luminus Technical University, Amman 11118, JordanCollege of Computing and Information Technology, Shaqra University, Riyadh 11911, Saudi ArabiaDepartment of Computer Science and Digital Technologies, Faculty of Engineering and Environment, Northumbria University, Newcastle upon Tyne NE1 8ST, UKDeveloping an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field.https://www.mdpi.com/2227-9709/10/1/28data augmentationGANsmedical datasetmachine learninghealthcare |
| spellingShingle | Mohammad Alauthman Ahmad Al-qerem Bilal Sowan Ayoub Alsarhan Mohammed Eshtay Amjad Aldweesh Nauman Aslam Enhancing Small Medical Dataset Classification Performance Using GAN Informatics data augmentation GANs medical dataset machine learning healthcare |
| title | Enhancing Small Medical Dataset Classification Performance Using GAN |
| title_full | Enhancing Small Medical Dataset Classification Performance Using GAN |
| title_fullStr | Enhancing Small Medical Dataset Classification Performance Using GAN |
| title_full_unstemmed | Enhancing Small Medical Dataset Classification Performance Using GAN |
| title_short | Enhancing Small Medical Dataset Classification Performance Using GAN |
| title_sort | enhancing small medical dataset classification performance using gan |
| topic | data augmentation GANs medical dataset machine learning healthcare |
| url | https://www.mdpi.com/2227-9709/10/1/28 |
| work_keys_str_mv | AT mohammadalauthman enhancingsmallmedicaldatasetclassificationperformanceusinggan AT ahmadalqerem enhancingsmallmedicaldatasetclassificationperformanceusinggan AT bilalsowan enhancingsmallmedicaldatasetclassificationperformanceusinggan AT ayoubalsarhan enhancingsmallmedicaldatasetclassificationperformanceusinggan AT mohammedeshtay enhancingsmallmedicaldatasetclassificationperformanceusinggan AT amjadaldweesh enhancingsmallmedicaldatasetclassificationperformanceusinggan AT naumanaslam enhancingsmallmedicaldatasetclassificationperformanceusinggan |