GANs 'N Lungs: improving pneumonia prediction

1 Aug 2019 · Tatiana Malygina, Elena Ericheva, Ivan Drokin ·

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.

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Binary Classification

Data Augmentation

General Classification

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

Batch Normalization • Convolution • Cycle Consistency Loss • CycleGAN • GAN • GAN Least Squares Loss • Instance Normalization • Leaky ReLU • PatchGAN • ReLU • Residual Block • Residual Connection • Sigmoid Activation • Tanh Activation