Lung image segmentation by generative adversarial networks

TL;DR

This paper introduces a lung image segmentation approach using generative adversarial networks, leveraging their image translation ability to improve segmentation accuracy in medical imaging.

Contribution

The paper presents a novel application of GANs for lung image segmentation, demonstrating superior performance over existing methods.

Findings

Effective segmentation on real lung datasets

Outperforms state-of-the-art methods

Validates GANs for medical image segmentation

Abstract

Lung image segmentation plays an important role in computer-aid pulmonary diseases diagnosis and treatment. This paper proposed a lung image segmentation method by generative adversarial networks. We employed a variety of generative adversarial networks and use its capability of image translation to perform image segmentation. The generative adversarial networks was employed to translate the original lung image to the segmented image. The generative adversarial networks based segmentation method was test on real lung image data set. Experimental results shows that the proposed method is effective and outperform state-of-the art method.