Semantics Guided Disentangled GAN for Chest X-ray Image Rib Segmentation

TL;DR

This paper introduces SD-GAN, a semantics-guided disentangled GAN that generates high-quality chest X-ray images with organ-specific details, improving rib segmentation accuracy with limited annotated data.

Contribution

The paper proposes a novel SD-GAN that leverages semantic guidance and feature disentanglement for realistic chest X-ray image synthesis, along with a new dataset and a specialized segmentation network.

Findings

SD-GAN produces high-quality organ-specific chest X-ray images.

Generated data enhances segmentation performance of MTUNet.

The approach outperforms existing methods in rib segmentation accuracy.

Abstract

The label annotations for chest X-ray image rib segmentation are time consuming and laborious, and the labeling quality heavily relies on medical knowledge of annotators. To reduce the dependency on annotated data, existing works often utilize generative adversarial network (GAN) to generate training data. However, GAN-based methods overlook the nuanced information specific to individual organs, which degrades the generation quality of chest X-ray image. Hence, we propose a novel Semantics guided Disentangled GAN (SD-GAN), which can generate the high-quality training data by fully utilizing the semantic information of different organs, for chest X-ray image rib segmentation. In particular, we use three ResNet50 branches to disentangle features of different organs, then use a decoder to combine features and generate corresponding images. To ensure that the generated images correspond to the input organ labels in semantics tags, we employ a semantics guidance module to perform semantic guidance on the generated images. To evaluate the efficacy of SD-GAN in generating high-quality samples, we introduce modified TransUNet(MTUNet), a specialized segmentation network designed for multi-scale contextual information extracting and multi-branch decoding, effectively tackling the challenge of organ overlap. We also propose a new chest X-ray image dataset (CXRS). It includes 1250 samples from various medical institutions. Lungs, clavicles, and 24 ribs are simultaneously annotated on each chest X-ray image. The visualization and quantitative results demonstrate the efficacy of SD-GAN in generating high-quality chest X-ray image-mask pairs. Using generated data, our trained MTUNet overcomes the limitations of the data scale and outperforms other segmentation networks.