GAN-Based Approaches for Generating Structured Data in the Medical Domain

Abstract:
        Modern machine and deep learning methods require large datasets to achieve reliable and robust results. This requirement is often difficult to meet in the medical field, due to data sharing limitations imposed by privacy regulations or the presence of a small number of patients (e.g., rare diseases). To address this data scarcity and to improve the situation, novel generative models such as Generative Adversarial Networks (GANs) have been widely used to generate synthetic data that mimic real data by representing features that reflect health-related information without reference to real patients. In this paper, we consider several GAN models to generate synthetic data used for training binary (malignant/benign) classifiers, and compare their performances in terms of classification accuracy with cases where only real data are considered. We aim to investigate how synthetic data can improve classification accuracy, especially when a small amount of data is available. To this end, we have developed and implemented an evaluation framework where binary classifiers are trained on extended datasets containing both real and synthetic data. The results show improved accuracy for classifiers trained with generated data from more advanced GAN models, even when limited amounts of original data are available.

DOI: 10.3390/app12147075

Projects: Synthetica: generation and evaluation of synthetic data

Publication type: Journal article

Journal: Applied Sciences

Human Diseases: No Human Disease specified

Citation: Applied Sciences 12(14):7075

Date Published: 1st Jul 2022

URL: https://gitlab.com/ul-mds/data-science/synthetic-data/gan-collection

Registered Mode: by DOI

Authors: Masoud Abedi, Lars Hempel, Sina Sadeghi, Toralf Kirsten

Help
Citation
Abedi, M., Hempel, L., Sadeghi, S., & Kirsten, T. (2022). GAN-Based Approaches for Generating Structured Data in the Medical Domain. In Applied Sciences (Vol. 12, Issue 14, p. 7075). MDPI AG. https://doi.org/10.3390/app12147075
Activity

Views: 918

Created: 11th Sep 2023 at 10:12

Last updated: 11th Sep 2023 at 10:20

help Tags

This item has not yet been tagged.

help Attributions

None

Related links

Related items

Powered by
(v.1.13.0-master)
Copyright © 2008 - 2021 The University of Manchester and HITS gGmbH
Institute for Medical Informatics, Statistics and Epidemiology, University of Leipzig

By continuing to use this site you agree to the use of cookies