# Informative sample generation using class aware generative adversarial networks for classification of chest Xrays

## TL;DR

This paper introduces an active learning framework combined with a class-aware GAN to generate realistic chest X-ray images, effectively addressing class imbalance and improving disease classification with less data.

## Contribution

It presents a novel combination of active learning and class-aware GANs for data augmentation in medical imaging, enhancing classification performance with fewer labeled samples.

## Key findings

- Achieves state-of-the-art performance using only 35% of the dataset.
- Effective data augmentation improves disease detection accuracy.
- Reduces data annotation effort significantly.

## Abstract

Training robust deep learning (DL) systems for disease detection from medical images is challenging due to limited images covering different disease types and severity. The problem is especially acute, where there is a severe class imbalance. We propose an active learning (AL) framework to select most informative samples for training our model using a Bayesian neural network. Informative samples are then used within a novel class aware generative adversarial network (CAGAN) to generate realistic chest xray images for data augmentation by transferring characteristics from one class label to another. Experiments show our proposed AL framework is able to achieve state-of-the-art performance by using about $35\%$ of the full dataset, thus saving significant time and effort over conventional methods.