medical-7

Medical Image Generation

3260 papers • 126 benchmarks • 313 datasets

Medical image generation is the task of synthesising new medical images. ( Image credit: Towards Adversarial Retinal Image Synthesis )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in medical-image-generation-7

Trend

Dataset

Best Model

Actions

SLIVER07

ACDC

ChestXray14 1024x1024

Libraries

i

Use these libraries to find medical-image-generation-7 models and implementations

Datasets

ChestX-ray14

ACDC

BCI

Leishmania parasite dataset

Subtasks

Radiologist Binary Classification

Most implemented papers

NiftyNet: a deep-learning platform for medical imaging

Z. Eaton-Rosen, M. Modat, P. Nachev, D. Barratt, Guotai Wang, Eli Gibson, Wenqi Li, Carole H. Sudre, Lucas Fidon, D. I. Shakir, Robert Gray, T. Doel, Yipeng Hu, Tom Whyntie, S. Ourselin, M. J. Cardoso, Tom Vercauteren•Sun Sep 10 2017

An open-source platform is implemented based on TensorFlow APIs for deep learning in medical imaging domain that facilitates warm starts with established pre-trained networks, adapting existing neural network architectures to new problems, and rapid prototyping of new solutions.

Content

Chest X-Ray Images (Pneumonia)

ChestX-ray14

557

0

Paper Graph

PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation

Q. Dou, P. Heng, Hao Chen, Ben Glocker, X. Zhuang, C. Ouyang, Cheng Chen•Tue Dec 18 2018

This paper proposes the PnPAdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e.g., MRI and CT, and introduces a novel benchmark on the cardiac dataset for the task of unsupervised cross-modality domain adaptation.

51 0

Paper Graph

Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT

Per Welander, Simon Karlsson, A. Eklund•Tue Jun 19 2018

It is shown that the implemented GAN models can synthesize visually realistic MR images (incorrectly labeled as real by a human) and it is also shown that models producing more visually realistic synthetic images not necessarily have better quantitative error measurements, when compared to ground truth data.

110 0

Paper Graph

Skin Lesion Synthesis with Generative Adversarial Networks

S. Avila, Fábio Perez, Eduardo Valle, Alceu Bissoto•Sat Sep 15 2018

To the best of the knowledge, the results are the first to show visually-appealing synthetic images that comprise clinically-meaningful information on automated skin cancer classification.

109 0

Paper Graph

ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

S. K. Zhou, Jiebo Luo, Jianbo Yuan, Haofu Liao, Wei-An Lin•Tue Jun 04 2019

A novel artifact disentanglement network that disentangles the metal artifacts from CT images in the latent space is introduced that achieves comparable performance to existing supervised models for MAR and demonstrates better generalization ability over the supervised models.

165 0

Paper Graph

Synthetic Medical Images from Dual Generative Adversarial Networks

John Guibas, T. Virdi, Peter S. Li•Tue Sep 05 2017

A novel, two-stage pipeline for generating synthetic medical images from a pair of generative adversarial networks, tested in practice on retinal fundi images and develops a hierarchical generation process to divide the complex image generation task into two parts: geometry and photorealism.

181 0

Paper Graph

Towards Adversarial Retinal Image Synthesis

M. Abràmoff, M. Niemeijer, A. Campilho, P. Costa, A. Galdrán, Maria Inês Meyer, A. Mendonça•Mon Jan 30 2017

This work proposes a method that learns to synthesize eye fundus images directly from data, by means of a vessel segmentation technique that uses a recent image-to-image translation technique, based on the idea of adversarial learning.

128 0

Paper Graph

Generative Adversarial Network in Medical Imaging: A Review

Xin Yi, Ekta Walia, P. Babyn•Tue Sep 18 2018

A review of recent advances in medical imaging using the adversarial training scheme with the hope of benefiting researchers interested in this technique.

1567 0

Paper Graph

Melanoma detection using adversarial training and deep transfer learning

H. Zunair, Benourida Hamza•Sun Apr 05 2020

Interestingly, it is shown that the proposed two-stage framework for automatic classification of skin lesion images using adversarial training and transfer learning toward melanoma detection leads to context based lesion assessment that can reach an expert dermatologist level.

102 0

Paper Graph

Adding a benchmark result helps the community track progress.