Abstract
In recent years, deep learning (DL) has been recognized very useful in the semantic segmentation of biomedical images. Such an application, however, is significantly hindered by the lack of pixel-wise annotations. In this work, we propose a data pair generative adversarial network (DPGAN) for the purpose of synthesizing concurrently the diverse biomedical images and the segmentation labels from random latent vectors. First, a hierarchical structure is constructed consisting of three variational auto-encoder generative adversarial networks (VAEGANs) with an extra discriminator. Subsequently, to alleviate the influence from the imbalance between lesions and non-lesions areas in biomedical segmentation data sets, we divide the DPGAN into three stages, namely, background stage, mask stage and advanced stage, with each stage deploying a VAEGAN. In such a way, a large number of new segmentation data pairs are generated from random latent vectors and then used to augment the original data sets. Finally, to validate the effectiveness of the proposed DPGAN, experiments are carried out on a vestibular schwannoma data set, a kidney tumor data set and a skin cancer data set. The results indicate that, in comparison to other state-of-the-art GAN-based methods, the proposed DPGAN shows better performance in the generative quality, and meanwhile, gains an effective boost on semantic segmentation of class imbalanced biomedical images.
•A data pair generative adversarial network (DPGAN) is proposed.•The DPGAN is divided into background, mask and advanced stages.•Experiments are carried out on three real-world data sets.•The DPGAN shows better performance in the generative quality.•Semantic segmentation is improved on class imbalanced biomedical images.