GANs 'N Lungs: improving pneumonia prediction

Abstract

We propose a novel method to improve deep learning model performance on highly-imbalanced tasks. The proposed method is based on CycleGAN to achieve balanced dataset. We show that data augmentation with GAN helps to improve accuracy of pneumonia binary classification task even if the generative network was trained on the same training dataset.

Accepted as an extended abstract for MIDL 2019 [arXiv:1907.08612]