A multi-stage GAN for multi-organ chest X-ray image generation and segmentation

TL;DR

This paper introduces a multi-stage GAN approach for generating synthetic multi-organ chest X-ray images and labels, improving segmentation performance especially with limited training data.

Contribution

A novel multi-stage GAN method that enhances synthetic image and label generation for small datasets, advancing multi-organ chest X-ray segmentation.

Findings

Multistage GAN outperforms single-stage in small data regimes.

Synthetic data improves segmentation accuracy.

Method achieves state-of-the-art results on chest X-ray segmentation.

Abstract

Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resources and the time required for labeling. In this paper, we present a novel multi-stage generation algorithm based on Generative Adversarial Networks (GANs) that can produce synthetic images along with their semantic labels and can be used for data augmentation. The main feature of the method is that, unlike other approaches, generation occurs in several stages, which simplifies the procedure and allows it to be used on very small datasets. The method has been evaluated on the segmentation of chest radiographic images, showing promising results. The multistage approach achieves state-of-the-art and, when very few images are used to train the GANs, outperforms the corresponding single-stage approach.