MedGAN: Medical Image Translation using GANs

Abstract

Image-to-image translation is considered a new frontier in the field of medical image analysis, with numerous potential applications. However, a large portion of recent approaches offers individualized solutions based on specialized task-specific architectures or require refinement through non-end-to-end training. In this paper, we propose a new framework, named MedGAN, for medical image-to-image translation which operates on the image level in an end-to-end manner. MedGAN builds upon recent advances in the field of generative adversarial networks (GANs) by merging the adversarial framework with a new combination of non-adversarial losses. We utilize a discriminator network as a trainable feature extractor which penalizes the discrepancy between the translated medical images and the desired modalities. Moreover, style-transfer losses are utilized to match the textures and fine-structures of the desired target images to the translated images. Additionally, we present a new generator architecture, titled CasNet, which enhances the sharpness of the translated medical outputs through progressive refinement via encoder-decoder pairs. Without any application-specific modifications, we apply MedGAN on three different tasks: PET-CT translation, correction of MR motion artefacts and PET image denoising. Perceptual analysis by radiologists and quantitative evaluations illustrate that the MedGAN outperforms other existing translation approaches.

16 pages, 8 figures

References in corpus (2)

• Improving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgeries
• Adversarial Sparse-View CBCT Artifact Reduction

Cited by in corpus (30)

• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• ResViT: Residual vision transformers for multi-modal medical image synthesis
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• Diffusion Probabilistic Models beat GANs on Medical Images
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
• Explainable Diabetic Retinopathy Detection and Retinal Image Generation
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• 3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
• Low-field magnetic resonance image enhancement via stochastic image quality transfer
• Cephalogram Synthesis and Landmark Detection in Dental Cone-Beam CT Systems
• Efficient CNN-based Super Resolution Algorithms for mmWave Mobile Radar Imaging
• SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking
• AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks
• Dual-cycle Constrained Bijective VAE-GAN For Tagged-to-Cine Magnetic Resonance Image Synthesis
• Deep Learning in Mining Biological Data
• Bridging the gap between paired and unpaired medical image translation
• Ultrasound Image Enhancement using CycleGAN and Perceptual Loss
• A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
• HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis
• Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs
• CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation
• Muographic Image Upsampling with Machine Learning for Built Infrastructure Applications
• Quantifying the effect of X-ray scattering for data generation in real-time defect detection
• Anatomical feature-prioritized loss for enhanced MR to CT translation
• Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets
• The Quest for Early Detection of Retinal Disease: 3D CycleGAN-based Translation of Optical Coherence Tomography into Confocal Microscopy
• Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imaging
• Systole-Conditioned Generative Cardiac Motion
• Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
• Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET