Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging

@article{McDonagh2017ContextSensitiveSF,
  title={Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging},
  author={Steven G. McDonagh and Benjamin Hou and Amir Alansary and Ozan Oktay and Konstantinos Kamnitsas and Mary A. Rutherford and Joseph V. Hajnal and Bernhard Kainz},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.00035}
}
3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast but low-resolution image acquisition and highly detailed but slow image acquisition. Fast imaging is required for targets that move to avoid motion artefacts. This is in particular difficult for fetal MRI. Spatially independent upsampling techniques, which are the state-of-the-art to address this problem, are error prone and disregard contextual information. In this paper we propose a context-sensitive upsampling method based… 

Self-Supervised Isotropic Superresolution Fetal Brain MRI

This paper provides a proof of concept of a self-supervised single-volume superresolution framework for T2-weighted FBMRI (SAIR) and validate SAIR quantitatively in a motion-free simulated environment, and results suggest SAIR could be incor-porated into current reconstruction pipelines.

Deep robust residual network for super-resolution of 2D fetal brain MRI

A robust residual-learning SR network to generate a sharp HR brain image from an LR input is studied to increase the quality of brain MRI and improve the robustness of the model and enhance the texture information of SR results.

Gradient-Guided Convolutional Neural Network for MRI Image Super-Resolution

A gradient-guided convolutional neural network is developed for improving the reconstruction accuracy of high-frequency image details from the LR image and achieves better performance over the published state-of-art approaches.

Super-resolution reconstruction of MR image with a novel residual learning network algorithm

This work proposes a novel residual learning-based SR algorithm for MRI, which combines both multi-scale GRL and shallow network block-based local residual learning (LRL), which works effectively in capturing high-frequency details by learning local residuals.

Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction

A novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction is proposed and is shown how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix and explicit multi-contrast relationship matrix into account during the end-to-end optimization.

MR Image Super-Resolution via Wide Residual Networks With Fixed Skip Connection

A progressive wide residual network with a fixed skip connection (named FSCWRN) based SR algorithm is proposed to reconstruct MR images, which combines the global residual learning and the shallow network based local residual learning.

Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network

Extensive experiments demonstrate that the proposed MINet outperforms state-of-the-art multi-contrast MRI SR methods in terms of various metrics and the multi-stage integration module is able to excavate complex interactions among multi-Contrast features at different stages, leading to improved target-image quality.

Deep Robust Residual Network for Brain MRI Super-Resolution

This work studies a robust residual-learning SR network to generate a sharp HR brain image from an LR input and combines the Charbonnier loss and GDL to improve the robustness of the model and enhance the texture information of SR results.

References

SHOWING 1-10 OF 24 REFERENCES

Multi-input Cardiac Image Super-Resolution Using Convolutional Neural Networks

Experimental results show that the CNN model outperforms state-of-the-art SR methods in terms of image quality while being computationally efficient and that image segmentation and motion tracking benefits more from SR-CNN when it is used as an initial upscaling method than conventional interpolation methods for the subsequent analysis.

On Super-Resolution for Fetal Brain MRI

The approach, which consists of iterative motion correction and high resolution image estimation, is compared with a previously used scattered data interpolation-based reconstruction method and shows significant improvements in performance.

Robust Super-Resolution Volume Reconstruction From Slice Acquisitions: Application to Fetal Brain MRI

A novel technique based on a slice acquisition model, which enables the reconstruction of a volumetric image from multiple-scan slice acquisitions and a robust M-estimation solution which minimizes a robust error norm function between the model-generated slices and the acquired slices are developed.

Non-local MRI upsampling

Single Anisotropic 3-D MR Image Upsampling via Overcomplete Dictionary Trained From In-Plane High Resolution Slices

A novel single anisotropic 3-D MR image upsampling method via sparse representation and overcomplete dictionary that is trained from in-plane high resolution slices to upsample in the out-of-plane dimensions that is more accurate than classical interpolation and does not require extra training sets.

Super-Resolution in Medical Imaging

Research on super-resolution research in key medical imaging modalities, including MRI, fMRI and PET, has started to emerge in recent years and is reviewed herein.

Intersection Based Motion Correction of Multislice MRI for 3-D in Utero Fetal Brain Image Formation

An alternative approach to slice intersection motion correction (SIMC), that seeks to directly co-align multiple slice stacks by considering the matching structure along all intersecting slice pairs in all orthogonally planned slices that are acquired in clinical imaging studies, is described.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.