3N-GAN: Semi-Supervised Classification of X-Ray Images with a 3-Player Adversarial Framework

TL;DR

3N-GAN introduces a novel three-player adversarial framework for semi-supervised classification of medical images, effectively leveraging unlabeled data in fully-supervised settings to improve performance.

Contribution

It proposes a new 3-player GAN architecture that enhances semi-supervised medical image classification by integrating a classifier into the adversarial training process.

Findings

Improved classification accuracy over existing algorithms

Enhanced quality of generated images

Seamless integration with other medical imaging models

Abstract

The success of deep learning for medical imaging tasks, such as classification, is heavily reliant on the availability of large-scale datasets. However, acquiring datasets with large quantities of labeled data is challenging, as labeling is expensive and time-consuming. Semi-supervised learning (SSL) is a growing alternative to fully-supervised learning, but requires unlabeled samples for training. In medical imaging, many datasets lack unlabeled data entirely, so SSL can't be conventionally utilized. We propose 3N-GAN, or 3 Network Generative Adversarial Networks, to perform semi-supervised classification of medical images in fully-supervised settings. We incorporate a classifier into the adversarial relationship such that the generator trains adversarially against both the classifier and discriminator. Our preliminary results show improved classification performance and GAN generations over various algorithms. Our work can seamlessly integrate with numerous other medical imaging model architectures and SSL methods for greater performance.