CSE-GAN: A 3D conditional generative adversarial network with concurrent squeeze-and-excitation blocks for lung nodule segmentation

Lung nodule segmentation plays a crucial role in early-stage lung cancer diagnosis, and early detection of lung cancer can improve the survival rate of the patients. The approaches based on convolutional neural networks (CNN) have outperformed the traditional image processing approaches in various computer vision applications, including medical image analysis. Although multiple techniques based on convolutional neural networks have provided state-of-the-art performances for medical image segmentation tasks, these techniques still have some challenges. Two main challenges are data scarcity and class imbalance, which can cause overfitting resulting in poor performance. In this study, we propose an approach based on a 3D conditional generative adversarial network for lung nodule segmentation, which generates better segmentation results by learning the data distribution, leading to better accuracy. The generator in the proposed network is based on the famous U-Net architecture with a concurrent squeeze & excitation module. The discriminator is a simple classification network with a spatial squeeze & channel excitation module, differentiating between ground truth and fake segmentation. To deal with the overfitting, we implement patch-based training. We have evaluated the proposed approach on two datasets, LUNA16 data and a local dataset. We achieved significantly improved performances with dice coefficients of 80.74% and 76.36% and sensitivities of 85.46% and 82.56% for the LUNA test set and local dataset, respectively.