A Review on Deep Learning in Medical Image Reconstruction

@article{Zhang2019ARO,
  title={A Review on Deep Learning in Medical Image Reconstruction},
  author={Haimiao Zhang and Bin Dong},
  journal={Journal of the Operations Research Society of China},
  year={2019},
  volume={8},
  pages={311-340}
}
  • Haimiao Zhang, Bin Dong
  • Published 23 June 2019
  • Computer Science, Engineering, Physics
  • Journal of the Operations Research Society of China
Medical imaging is crucial in modern clinics to provide guidance to the diagnosis and treatment of diseases. Medical image reconstruction is one of the most fundamental and important components of medical imaging, whose major objective is to acquire high-quality medical images for clinical usage at the minimal cost and risk to the patients. Mathematical models in medical image reconstruction or, more generally, image restoration in computer vision have been playing a prominent role. Earlier… Expand
A survey on deep learning in medical image reconstruction
TLDR
Reconstruction methods improve the quality of reconstructed images qualitatively and quantitatively and the challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques. Expand
Deep learning for biomedical image reconstruction: a survey
TLDR
DL presents a promising approach to image reconstruction with artifact reduction and reconstruction speed-up reported in recent works as part of a rapidly growing field. Expand
Y-Net: Hybrid deep learning image reconstruction for photoacoustic tomography in vivo
TLDR
A new convolutional neural network (CNN) framework Y-Net is proposed: a CNN architecture to reconstruct the initial PA pressure distribution by optimizing both raw data and beamformed images once, which performs better than other existing methods. Expand
A Green Prospective for Learned Post-Processing in Sparse-View Tomographic Reconstruction
TLDR
A shallow neural network is proposed to perform efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm and is more robust than the widely used and very deep ResUNet for tomographic reconstructions from sparse-view protocols. Expand
Learned Full-Sampling Reconstruction From Incomplete Data
TLDR
Inspired by the success of deep learning methods in imaging, the convolutional neural networks are utilized to embed and learn both the interrelationship between raw data and reconstructed images and prior information such as regularization, which is implemented in an end-to-end training process. Expand
Compressive Imaging: Structure, Sampling, Learning
Accurate, robust and fast image reconstruction is a critical task in many scientific, industrial and medical applications. Over the last decade, image reconstruction has been revolutionized by theExpand
A Deep Learning Approach for the Photoacoustic Tomography Recovery From Undersampled Measurements
TLDR
A deep learning–based PAT (Deep-PAT) method that is not only able to reconstruct PAT from a fewer number of measurements without considering the prerequisite conditions of CS, but also can eliminate undersampled artifacts effectively. Expand
Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging - Mini Review, Comparison and Perspectives
TLDR
This chapter reviews the GAN powered fast MRI methods with a comparative study on various anatomical datasets to demonstrate the generalisability and robustness of this kind of fast MRI while providing future perspectives. Expand
A geometry-guided deep learning technique for CBCT reconstruction
TLDR
With much lower memory requirement compared to other existing networks, the GDL technique is demonstrated to be the first DL technique that can rapidly and accurately reconstruct CBCT images from sparsely sampled data. Expand
Radon Inversion via Deep Learning
TLDR
The experimental results demonstrate the feasibility of the proposed iRadonMAP framework for Radon inversion with deep learning techniques, and construct an interpretable neural network that contains three dedicated components. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 212 REFERENCES
End-to-End Abnormality Detection in Medical Imaging
TLDR
An end-to-end DNN was implemented for lung nodule detection in low-dose chest computed tomography (CT), where a numerical simulation was done to generate acquisitions from 1,018 chest CT images with radiologists' annotations. Expand
Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network
TLDR
This work combines the autoencoder, deconvolution network, and shortcut connections into the residual encoder–decoder convolutional neural network (RED-CNN) for low-dose CT imaging and achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Expand
A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution
TLDR
The proposed DD-Net method for sparse-view CT reconstruction achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation and can increase the structure similarity by up to 18% and reduce the root mean square error by up-to-42%. Expand
Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss
TLDR
This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity that is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Expand
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once. Expand
ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
TLDR
Due to the combination of the advantages in model-based approach and deep learning approach, the ADMM-Nets achieve state-of-the-art reconstruction accuracies with fast computational speed. Expand
JSR-Net: A Deep Network for Joint Spatial-radon Domain CT Reconstruction from Incomplete Data
  • Haimiao Zhang, Bin Dong, Baodong Liu
  • Computer Science, Physics
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
TLDR
A hybrid loss function is adopted to improve the performance of the JSR-Net making it more effective in protecting important image structures, as well as a recently proposed deep model. Expand
Deep ADMM-Net for Compressive Sensing MRI
TLDR
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed. Expand
End-to-End Lung Nodule Detection in Computed Tomography
TLDR
A deep-neural-network-based detection system for lung nodule detection in computed tomography (CT) and could be expanded to most detection tasks in medical imaging. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
...
1
2
3
4
5
...