Addressing Small and Imbalanced Medical Image Datasets Using Generative Models: A Comparative Study of DDPM and PGGANs with Random and Greedy K Sampling

TL;DR

This study compares DDPM and PGGAN generative models for augmenting small, imbalanced medical image datasets, demonstrating DDPM's superior image quality and its positive impact on classification accuracy.

Contribution

It introduces a framework for evaluating synthetic medical images and shows DDPM's effectiveness in improving model performance over PGGANs.

Findings

DDPM produces more realistic images with lower FID scores.

Synthetic images from DDPM improve classification accuracy by up to 6%.

Random Sampling provides more stable augmentation results.

Abstract

The development of accurate medical image classification models is often constrained by privacy concerns and data scarcity for certain conditions, leading to small and imbalanced datasets. To address these limitations, this study explores the use of generative models, such as Denoising Diffusion Probabilistic Models (DDPM) and Progressive Growing Generative Adversarial Networks (PGGANs), for dataset augmentation. The research introduces a framework to assess the impact of synthetic images generated by DDPM and PGGANs on the performance of four models: a custom CNN, Untrained VGG16, Pretrained VGG16, and Pretrained ResNet50. Experiments were conducted using Random Sampling and Greedy K Sampling to create small, imbalanced datasets. The synthetic images were evaluated using Frechet Inception Distance (FID) and compared to original datasets through classification metrics. The results show that DDPM consistently generated more realistic images with lower FID scores and significantly outperformed PGGANs in improving classification metrics across all models and datasets. Incorporating DDPM-generated images into the original datasets increased accuracy by up to 6%, enhancing model robustness and stability, particularly in imbalanced scenarios. Random Sampling demonstrated superior stability, while Greedy K Sampling offered diversity at the cost of higher FID scores. This study highlights the efficacy of DDPM in augmenting small, imbalanced medical image datasets, improving model performance by balancing the dataset and expanding its size.