Awesome GAN for Medical Imaging

A curated list of awesome GAN resources in medical imaging, inspired by the other awesome-* initiatives.

For a complete list of GANs in general computer vision, please visit really-awesome-gan.

To complement or correct it, please contact me at xiy525@mail.usask.ca or send a pull request.

Overview

• Review
• Low Dose CT Denoising
• Segmentation
• Detection
• Medical Image Synthesis
• Reconstruction
• Classification
• Registration
• Others

Review

• [Generative Adversarial Network in Medical Imaging: A Review] [scholar] [MedIA]
• [GANs for Medical Image Analysis] [scholar] [arXiv]
• [Generative adversarial networks and adversarial methods in biomedical image analysis] [scholar] [arXiv]

Low Dose CT Denoising

• [Generative Adversarial Networks for Noise Reduction in Low-Dose CT] [scholar] [TMI]
• [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss] [scholar] [arXiv]
• [Sharpness-aware Low dose CT denoising using conditional generative adversarial network] [scholar] [arXiv] [JDI] [code]
• [Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography] [scholar] [arXiv]
• [Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising] [scholar] [arXiv]
• [3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network] [scholar] [arXiv]
• [CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement] [scholar] [MLMI2018]
• [TomoGAN: Low-Dose X-Ray Tomography with Generative Adversarial Networks] [scholar] [arXiv]

Segmentation

• [SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation] [scholar] [arXiv]
• [Adversarial training and dilated convolutions for brain MRI segmentation] [scholar] [arXiv]
• [Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks] [scholar] [arXiv]
• [Automatic Liver Segmentation Using an Adversarial Image-to-Image Network] [scholar] [arXiv]
• [Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images] [scholar] [MICCAI17]
• [SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays] [scholar] [arXiv]
• [Adversarial Deep Structured Nets for Mass Segmentation from Mammograms] [scholar] [arXiv] [code]
• [Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground Truth] [scholar] [arXiv]
• [Adversarial neural networks for basal membrane segmentation of microinvasive cervix carcinoma in histopathology images] [scholar] [ICMLC]
• [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks] [scholar] [IPMI2017]
• [whole heart and great vessel segmentation with context aware generative adversarial network] [scholar] [BM]
• [Generative Adversarial Neural Networks for Pigmented and Non-Pigmented Skin Lesions Detection in Clinical Images] [scholar] [CSCS2017]
• [Generative Adversarial Networks to Segment Skin Lesions] [scholar] [ISBI2018]
• [A conditional adversarial network for semantic segmentation of brain tumor] [scholar] [arXiv]
• [Brain Tumor Segmentation Using an Adversarial Network] [scholar] [MICCAI Brainlesion workshop]
• [Joint Optic Disc and Cup Segmentation using Fully Convolutional and Adversarial Networks] [scholar] [OMIA2017]
• [Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks] [scholar] [SPIE MI]
• [CC-GAN A Robust Transfer-Learning Framework for HEp-2 Specimen Image Segmentation] [scholar] [TA]
• [Conditional Generative Refinement Adversarial Networks for Unbalanced Medical Image Semantic Segmentation] [scholar] [arXiv]
• [Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning] [scholar] [arXiv]
• [Multi-input and dataset-invariant adversarial learning (MDAL) for left and right-ventricular coverage estimation in cardiac MRI] [scholar] [MICCAI2018]
• [Spine-GAN: Semantic segmentation of multiple spinal structures] [scholar] [MedIA]
• [Adversarial Networks for the Detection of Aggressive Prostate Cancer] [scholar] [arXiv]

Detection

• [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery] [scholar] [arXiv]
• [Generative adversarial networks for brain lesion detection] [scholar] [JMI]
• [Visual Feature Attribution using Wasserstein GANs] [scholar] [arXiv]
• [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders] [scholar] [arXiv]
• [Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior] [scholar] [arXiv]
• [Deep Adversarial Context-Aware Landmark Detection for Ultrasound Imaging] [scholar] [arXiv]

Medical Image Synthesis

• [Medical Image Synthesis with Context-Aware Generative Adversarial Networks] [scholar] [arXiv]
• [Medical Image Synthesis with Deep Convolutional Adversarial Networks] [scholar] [TBME] (published vision of the above preprint)
• [Deep MR to CT Synthesis using Unpaired Data] [scholar] [arXiv]
• [Synthesizing Filamentary Structured Images with GANs] [scholar] [arXiv] [code]
• [Synthesizing retinal and neuronal images with generative adversarial nets] [scholar] [MedIA] (published vision of the above preprint)
• [Synthesis of Positron Emission Tomography (PET) Images via Multi-channel Generative Adversarial Networks] [scholar] (GANs) [arXiv]
• [Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks] [scholar] [arXiv]
• [Synthetic Medical Images from Dual Generative Adversarial Networks] [scholar] [arXiv]
• [Virtual PET Images from CT Data Using Deep Convolutional Networks: Initial Results] [scholar] [arXiv]
• [Towards Adversarial Retinal Image Synthesis] [scholar] [arXiv]
• [End-to-end Adversarial Retinal Image Synthesis] [scholar] [TMI] (published vision of the above preprint)
• [Adversarial Image Synthesis for Unpaired Multi-Modal Cardiac Data] [scholar] [SASHIMI 2017]
• [Biomedical Data Augmentation Using Generative Adversarial Neural Networks] [scholar] [ICANN 2017]
• [Towards Virtual H&E Staining of Hyperspectral Lung Histology Images Using Conditional Generative Adversarial Networks] [scholar] [ICCV2017 workshop]
• [How to Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test for Lung Cancer Diagnosis] [scholar] [arXiv]
• [Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training] [scholar] [arXiv]
• [Unsupervised Histopathology Image Synthesis] [scholar] [arXiv]
• [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks] [scholar] [arXiv]
• [Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network] [scholar] [arXiv]
• [Towards cross-modal organ translation and segmentation: A cycle- and shape-consistent generative adversarial network] [scholar] [MedIA]
• [MRI Image-to-Image Translation for Cross-Modality Image Registration and Segmentation] [scholar] [arXiv]
• [Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size] [scholar] [arXiv]
• [Cross-Modality Synthesis from CT to PET using FCN and GAN Networks for Improved Automated Lesion Detection] [scholar] [arXiv]
• [MelanoGANs: High Resolution Skin Lesion Synthesis with GANs] [scholar] [arXiv]
• [Domain-adversarial neural networks to address the appearance variability of histopathology images] [scholar] [arXiv]
• [Neural Stain-Style Transfer Learning using GAN for Histopathological Images] [scholar] [arXiv]
• [Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI] [scholar] [arXiv]
• [Histopathology Stain-Color Normalization Using Generative Neural Networks] [scholar] [MIDL2018]
• [3D cGAN based cross-modality MR image synthesis for brain tumor segmentation] [scholar] [ISBI2018]
• [Deep CT to MR Synthesis using Paired and Unpaired Data] [scholar] [arXiv]
• [GAN-based synthetic brain MR image generation] [scholar] [ISBI2018]
• [StainGAN: Stain Style Transfer for Digital Histological Images] [scholar] [arXiv]
• [Adversarial Stain Transfer for Histopathology Image Analysis] [scholar] [TMI]
• [Chest x-ray generation and data augmentation for cardiovascular abnormality classification] [scholar] [SPIE MI2018]
• [blood vessel geometry synthesis using generative adversarial networks] [scholar] [MIDL2018]
• [Synergistic Reconstruction and Synthesis via Generative Adversarial Networks for Accelerated Multi-Contrast MRI] [scholar] [arXiv]
• [Stain normalization of histopathology images using generative adversarial networks] [scholar] [ISBI2018]
• [MedGAN: Medical Image Translation using GANs] [scholar] [arXiv]
• [Retinal Image Synthesis for CAD Development] [scholar] [ICIAR]
• [High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks] [scholar] [arXiv]
• [High-resolution medical image synthesis using progressively grown generative adversarial networks] [scholar] [arXiv]
• [Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training] [scholar] [MICCAI2018]
• [Generation of structural MR images from amyloid PET: Application to MR-less quantification] [scholar] [JNM]
• [Task Driven Generative Modeling for Unsupervised Domain Adaptation Application to X-ray Image Segmentation] [scholar] [arXiv]
• [Exploring the potential of generative adversarial networks for synthesizing radiological images of the spine to be used in in silico trials] [scholar] [FBB]
• [Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation] [scholar] [arXiv]
• [Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks] [scholar] [arXiv]
• [Learning implicit brain MRI manifolds with deep learning] [scholar] [SPIE MI2018]
• [Optimized generation of high-resolution phantom images using cGAN: Application to quantification of Ki67 breast cancer images] [scholar] [PloS one]
• [Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images-A Comparison of CycleGAN and UNIT] [scholar] [arXiv] [code]
• [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks] [scholar] [SASHIMI2018]
• [Generating Diffusion MRI scalar maps from T1 weighted images using generative adversarial networks] [scholar] [arXiv]
• [Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images] [scholar] [MICCAI2018]
• [An Adversarial Learning Approach to Medical Image Synthesis for Lesion Removal] [scholar] [arXiv]
• [Craniomaxillofacial Bony Structures Segmentation from MRI with Deep-Supervision Adversarial Learning] [scholar] [MICCAI2018]
• [Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network] [scholar] [MICCAI2018]
• [GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks] [scholar] [arXiv]
• [Generating Highly Realistic Images of Skin Lesions with GANs] [scholar] [CARE2018]
• [Generative Adversarial Network for Medical Images (MI-GAN)] [scholar] [JMS]
• [Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach] [scholar] [arXiv]
• [SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth] [scholar] [TMI]
• [Synthesizing Missing PET from MRI with Cycle-consistent Generative Adversarial Networks for Alzheimer's Disease Diagnosis] [scholar] [MICCAI2018]
• [Tumor-Aware, Adversarial Domain Adaptation from CT to MRI for Lung Cancer Segmentation] [scholar] [MICCAI2018]
• [Unpaired Brain MR-to-CT Synthesis Using a Structure-Constrained CycleGAN] [scholar] [DLMIA2018]
• [Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks] [scholar] [SASHIMI2018]
• [ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans] [scholar] [DLMIA2018]
• [Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy] [scholar] [PMB]
• [ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks] [scholar] [NeurIPS 2018 ML4H]
• [Red blood cell image generation for data augmentation using Conditional Generative Adversarial Networks] [scholar] [CVPR19 CVMI]
• [SUSAN: segment unannotated image structure using adversarial network] [scholar] [MRM]
• [CT synthesis from MR images for orthopedic applications in the lower arm using a conditional generative adversarial network] [scholar] [arXiv]
• [Learning Bone Suppression from Dual Energy Chest X-rays using Adversarial Networks] [scholar] [arXiv]
• [Simulating Patho-realistic Ultrasound Images using Deep Generative Networks with Adversarial Learning] [scholar] [ISBI2018]
• [Stain-transforming cycle-consistent generative adversarial networks for improved segmentation of renal histopathology] [MIDL2019]
• [Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization] [MIDL2019]
• [Image Synthesis with a Convolutional Capsule Generative Adversarial Network] [MIDL2019]
• [CT-realistic data augmentation using generative adversarial network for robust lymph node segmentation] [scholar] [SPIE MI2019]
• [Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations] [MIDL2019]
• [DavinciGAN: Unpaired Surgical Instrument Translation for Data Augmentation] [MIDL2019]
• [XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation] [MIDL2019]
• [Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss] [scholar] [arXiv]
• [CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation] [scholar] [MICCAI2018]
• [Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis] [scholar] [MICCAI SASHIMI 2019] [arXiv]
• [A modality conversion approach to MV-DRs and kV-DRRs registration using information bottlenecked conditional generative adversarial network] [scholar] [MP]

Reconstruction

• [Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks] [scholar] [arXiv]
• [Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss] [scholar] [TMI] (published version of the above preprint)
• [Deep Generative Adversarial Networks for Compressed Sensing (GANCS) Automates MRI] [scholar] [arXiv] [code]
• [Accelerated Magnetic Resonance Imaging by Adversarial Neural Network] [scholar] [DLMIA MICCAI 2017]
• [Deep De-Aliasing for Fast Compressive Sensing MR] [scholar] [arXiv]
• [3D conditional generative adversarial networks for high-quality PET image estimation at low dose] [scholar] [NI]
• [Improving resolution of MR images with an adversarial network incorporating images with different contrast] [scholar] [MP]
• [CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)] [scholar] [arXiv]
• [Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network] [scholar] [arXiv]
• [Sparse-View CT Reconstruction Using Wasserstein GANs] [scholar] [MLMIR 2018]
• [DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction] [scholar] [TMI] [code]
• [Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction] [scholar] [MICCAI2018]
• [Refacing: reconstructing anonymized facial features using GANs] [scholar] [arXiv]
• [Adversarial Inpainting of Medical Image Modalities] [scholar] [arXiv]
• [Adversarial Sparse-View CBCT Artifact Reduction] [scholar] [MICCAI2018]
• [Cardiac MR Motion Artefact Correction from K-space Using Deep Learning-Based Reconstruction] [scholar] [MLMIR 2018]
• [Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear] [scholar] [MICCAI2018]
• [Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network] [scholar] [MICCAI2018]
• [Multi-channel Generative Adversarial Network for Parallel Magnetic Resonance Image Reconstruction in K-space] [scholar] [MICCAI2018]
• [Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs] [scholar] [arXiv]
• [Brain MRI super-resolution using 3D generative adversarial networks] [scholar] [MIDL2018]
• [Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution] [scholar] [arXiv]
• [Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy] [scholar] [MIDL2018]
• [How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach] [scholar] [arXiv]
• [X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks] [scholar] [CVPR2019]

Classification

• [Semi-supervised Assessment of Incomplete LV Coverage in Cardiac MRI Using Generative Adversarial Nets] [scholar] [SASHIMI 2017]
• [Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks] [scholar] [arXiv]
• [Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks] [scholar] [arXiv] [code]
• [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification] [scholar] [arXiv]
• [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification] [scholar] [arXiv](extended version of above preprint)
• [Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification] [scholar] [arXiv]
• [Semi-supervised learning with generative adversarial networks for chest X-ray classification with ability of data domain adaptation] [scholar] [ISBI2018]
• [Generative adversarial learning for reducing manual annotation in semantic segmentation on large scale miscroscopy images: Automated vessel segmentation in retinal fundus image as test case] [scholar] [CVPRW2017]
• [Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images] [scholar] [NeurIPS 2018 ML4H]
• [Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease] [scholar] [NDM]
• [General-to-Detailed GAN for Infrequent Class Medical Images] [[scholar]](General-to-Detailed GAN for Infrequent Class Medical Images) [NeurIPS 2018 ML4H]
• [Towards generative adversarial networks as a new paradigm for radiology education] [scholar] [NeurIPS 2018 ML4H]
• [Abnormal Chest X-ray Identification With Generative Adversarial One-Class Classifier] [scholar] [ISBI2019]

Registration

• [Adversarial Image Registration with Application for MR and TRUS Image Fusion] [scholar] [arXiv]
• [Deformable medical image registration using generative adversarial networks] [scholar] [ISBI2018]
• [Generative Adversarial Networks for MR-CT Deformable Image Registration] [scholar] [arXiv]
• [Adversarial Deformation Regularization for Training Image Registration Neural Networks] [scholar] [MICCAI2018]
• [Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration] [scholar] [MICCAI2018]
• [Joint Registration And Segmentation Of Xray Images Using Generative Adversarial Networks] [scholar] [MLMI2018]

Others

• [Intraoperative Organ Motion Models with an Ensemble of Conditional Generative Adversarial Networks] [scholar] [arXiv]
• [Generative Spatiotemporal Modeling Of Neutrophil Behavior] [scholar] [ISBI2018]
• [Exploiting the potential of unlabeled endoscopic video data with self-supervised learning] [scholar] [IJCARS]
• [Adversarial Attacks Against Medical Deep Learning Systems] [scholar] [arXiv]
• [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation] [scholar] [MICCAI2018]
• [Generalizability vs. Robustness: Investigating Medical Imaging Networks Using Adversarial Examples] [scholar] [MICCAI2018]
• [CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning] [scholar] [arXiv]
• [Automated Treatment Planning in Radiation Therapy using Generative Adversarial Networks] [scholar] [NeurIPS 2018 ML4H]
• [Modelling the Progression of Alzheimer’s Disease in MRI Using Generative Adversarial Networks] [scholar] [SPIE MI2018]