Loading...
Dual-WGAN Ensemble Model for Alzheimer’s Dataset Augmentation with Minority Class Boosting
Ansari, Mohammad Samar Ilyas, Kulsum Aslam, Asra
Ansari, Mohammad Samar
Ilyas, Kulsum
Aslam, Asra
Citations
Altmetric:
Advisors
Editors
Other Contributors
EPub Date
Publication Date
2023-11-20
Submitted Date
Collections
Files
Other Titles
Abstract
Deep learning models have become very efficient and robust for several computer vision applications. However, to harness the benefits of state-of-art deep networks in the realm of disease detection and prediction, it is crucial that high-quality datasets be made available for the models to train on. This work recognizes the lack of training data (both in terms of quality and quantity of images) for using such networks for the detection of Alzheimer’s Disease. To address this issue, a Wasserstein Generative Adversarial Network (WGAN) is proposed to generate synthetic images for augmentation of an existing Alzheimer brain image dataset. The proposed approach is successful in generating high-quality images for inclusion in the Alzheimer image dataset, potentially making the dataset more suitable for training high-end models. This paper presents a two-fold contribution: (i) a WGAN is first developed for augmenting the non-dominant class (i.e. Moderate Demented) of the Alzheimer image dataset to bring the sample count (for that class) at par with the other classes, and (ii) another lightweight WGAN is used to augment the entire dataset for increasing the sample counts for all classes.
Citation
Ansari, M. S., Ilyas, K., & Aslam, A. (2023, 20-21 November). Dual-WGAN ensemble model for Alzheimer’s dataset augmentation with minority class boosting. 2023 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Sakheer, Bahrain, pp. 333-340. https://doi.org/10.1109/3ICT60104.2023.10391464
Publisher
IEEE
Journal
Research Unit
PubMed ID
PubMed Central ID
Type
Conference Contribution
Language
Description
Copyright © 2023, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Series/Report no.
ISSN
EISSN
2770-7466
ISBN
9798350307788