Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGAN

  title={Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGAN},
  author={Heng Liu and Jianyong Liu and Tao Tao and Shudong Hou and Jungong Han},
Due to the limitations of sensors, the transmission medium, and the intrinsic properties of ultrasound, the quality of ultrasound imaging is always not ideal, especially its low spatial resolution. To remedy this situation, deep learning networks have been recently developed for ultrasound image super-resolution (SR) because of the powerful approximation capability. However, most current supervised SR methods are not suitable for ultrasound medical images because the medical image samples are… 

Progressive Residual Learning With Memory Upgrade for Ultrasound Image Blind Super-Resolution

This work estimates the accurate blur kernel from the spatial attention map block of low resolution ultrasound image through a multi-label classification network, then constructs three modules–up- sampling (US) module, residual learning (RL) model and memory upgrading (MU) model for ultrasound image blind SR.

An enhanced multiscale generation and depth-perceptual loss-based super-resolution network for prostate ultrasound images

An enhanced multiscale generation and depth-perceptual loss-based super-resolution (SR) network for prostate ultrasound images (EGDL-CycleGAN) and the proposed approach is effective and superior to the bicubic classic image SR reconstruction algorithm, the SRGAN perception-driven method and the CycleGAN method applied to ultrasound images.

Toward extreme face super-resolution in the wild: A self-supervised learning approach

This work proposes a novel two-step extreme FSR by introducing a mid-resolution (MR) image as the stepping stone and extracting the latent codes from MR images and interpolating them in a self-supervised manner to facilitate artifact-suppressed image reconstruction.

Multimodal-Boost: Multimodal Medical Image Super-Resolution using Multi-Attention Network with Wavelet Transform

The proposed generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data and a learning method for training domain-specific classifiers as perceptual loss functions results in an efficient and reliable performance.

CycleGAN Clinical Image Augmentation Based on Mask Self-Attention Mechanism

This paper proposes a mask-based self-attention CycleGAN data augmentation method, which solves the problem of insufficient samples and data imbalance in the pneumonia dataset by generating high-quality pneumonia images.

Super-Resolution Ultrasound Imaging Scheme Based on a Symmetric Series Convolutional Neural Network

Experimental results show that the proposed SS-CNN achieves a high-quality reconstruction of the ultrasound image over the conventional methods in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), while providing compelling SR reconstruction time.

Patch Based Transformation for Minimum Variance Beamformer Image Approximation Using Delay and Sum Pipeline

This work proposes a patch level U-Net based neural network that treats the non-linear transformation of the RF data space that can account for the data driven weight adaptation done by the MVDR approach in the parameters of the network.

A Review of Self-supervised Learning Methods in the Field of Medical Image Analysis

  • Jiashu Xu
  • Computer Science
    International Journal of Image, Graphics and Signal Processing
  • 2021
This article provides the latest and most detailed overview of self-supervisedLearning in the medical field and promotes the development of unsupervised learning in the field of medical imaging with three categories: context-based, generation- based, and contrast-based.

Iterative facial image inpainting based on an encoder-generator architecture

This paper proposes an efficient solution to the facial image painting problem using the Cyclic Reverse Generator architecture, which provides an encoder-generator model that can compete with the state-of-the-art models both quantitatively and qualitatively.



Exploring Multi-scale Deep Encoder-Decoder and PatchGAN for Perceptual Ultrasound Image Super-Resolution

A new multi-scale deep encoder-decoder structure is incorporated into a PatchGAN (patch generative adversarial network) based framework for fast perceptual ultrasound image super-resolution (SR), which demonstrates its effectiveness and superiority, when compared to the most state-of-the-art methods.

Unsupervised Super-Resolution Framework for Medical Ultrasound Images Using Dilated Convolutional Neural Networks

  • Jingfeng LuWanyu Liu
  • Computer Science
    2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
  • 2018
A novel unsupervised super-resolution (USSR) framework to solve the single image super- resolution (SR) problem in ultrasound images which lack of training examples is presented, using the powerful nonlinear mapping ability of convolutional neural networks (CNNs), without relying on prior training or any external data.

Deep CNN-Based Ultrasound Super-Resolution for High-Speed High-Resolution B-Mode Imaging

This work adopts and modify the SRGAN to make B-mode US images of low lateral resolution similar to their original high-resolution (HR) images, and slightly modify the network architecture of SRGAN in order to efficiently improve the lateral resolution.

SRFeat: Single Image Super-Resolution with Feature Discrimination

A novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain and design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively.

To learn image super-resolution, use a GAN to learn how to do image degradation first

A two-stage process which firstly trains a High-to-Low Generative Adversarial Network to learn how to degrade and downsample high-resolution images requiring, during training, only unpaired high and low- Resolution images can be used to effectively increase the quality of real-world low- resolution images.

"Zero-Shot" Super-Resolution Using Deep Internal Learning

This paper exploits the internal recurrence of information inside a single image, and train a small image-specific CNN at test time, on examples extracted solely from the input image itself, which is the first unsupervised CNN-based SR method.

How Can We Make Gan Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach

A novel lesion focused SR (LFSR) method, which incorporates GAN to achieve perceptually realistic SISR results for brain tumour MRI images and a novel multi-scale GAN (MS-GAN), to achieve a more stabilised and efficient training and improved perceptual quality of the super-resolved results.

Fast simultaneous image super-resolution and motion deblurring with decoupled cooperative learning

This work proposes a deep decoupled cooperative learning model which can not only develop the corresponding recover network to deal with each degradation, but also flexibly handle multiple degradations at the same time.

Medical image super-resolution method based on dense blended attention network

The proposed method adds blended attention blocks to dense neural network(DenseNet), so that the neural network can concentrate more attention to the regions and channels with sufficient high-frequency details.

Image Super-Resolution Using Deep Convolutional Networks

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep