HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis

Abstract

Medical Image Synthesis (MIS) plays an important role in the intelligent medical field, which greatly saves the economic and time costs of medical diagnosis. However, due to the complexity of medical images and similar characteristics of different tissue cells, existing methods face great challenges in meeting their biological consistency. To this end, we propose the Hybrid Augmented Generative Adversarial Network (HAGAN) to maintain the authenticity of structural texture and tissue cells. HAGAN contains Attention Mixed (AttnMix) Generator, Hierarchical Discriminator and Reverse Skip Connection between Discriminator and Generator. The AttnMix consistency differentiable regularization encourages the perception in structural and textural variations between real and fake images, which improves the pathological integrity of synthetic images and the accuracy of features in local areas. The Hierarchical Discriminator introduces pixel-by-pixel discriminant feedback to generator for enhancing the saliency and discriminance of global and local details simultaneously. The Reverse Skip Connection further improves the accuracy for fine details by fusing real and synthetic distribution features. Our experimental evaluations on three datasets of different scales, i.e., COVID-CT, ACDC and BraTS2018, demonstrate that HAGAN outperforms the existing methods and achieves state-of-the-art performance in both high-resolution and low-resolution.

References in corpus (17)

• Improved Regularization of Convolutional Neural Networks with Cutout
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
• ResViT: Residual vision transformers for multi-modal medical image synthesis
• MedGAN: Medical Image Translation using GANs
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Learning Implicit Brain MRI Manifolds with Deep Learning
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Adversarial Inpainting of Medical Image Modalities
• High-resolution medical image synthesis using progressively grown generative adversarial networks
• Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs
• Adversarial Sparse-View CBCT Artifact Reduction
• Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning