Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network

TL;DR

This paper investigates how varying ratios of GAN-generated and real MRI images affect CNN-based brain tumor classification, demonstrating that moderate synthetic data augmentation improves performance, but excessive GAN data can impair generalization.

Contribution

It introduces a proportional sensitivity analysis of GAN-augmented data in CNN training for brain tumor classification, highlighting optimal synthetic data ratios for best performance.

Findings

Optimal performance with 900 real and 100 GAN images

Model maintains high accuracy with moderate GAN augmentation

Excessive GAN data reduces classification performance

Abstract

Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains high sensitivity and precision in tumor classification, even when trained predominantly on synthetic data. When only a small portion of GAN data was added, such as 900 real images and 100 GAN images, the model achieved excellent performance, with test accuracy reaching 95.2%, and precision, recall, and F1-score all exceeding 95%. However, as the proportion of GAN images increased further, performance gradually declined. This study suggests that while GANs are useful for augmenting limited datasets especially when real data is scarce, too much synthetic data can introduce artifacts that affect the model's ability to generalize to real world cases.