Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification

TL;DR

This paper introduces a GAN-based synthetic data augmentation approach that significantly improves liver lesion classification accuracy on limited CT datasets by increasing data diversity and size.

Contribution

The study proposes a novel training scheme combining classical and GAN-based augmentation for medical image classification.

Findings

Synthetic data augmentation improved sensitivity from 78.6% to 85.7%.

Specificity increased from 88.4% to 92.4%.

Method enhances classification performance on limited datasets.

Abstract

In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.