Dual Network Architecture for Few-view CT - Trained on ImageNet Data and Transferred for Medical Imaging

@article{Xie2019DualNA,
  title={Dual Network Architecture for Few-view CT - Trained on ImageNet Data and Transferred for Medical Imaging},
  author={Huidong Xie and Hongming Shan and Wenxiang Cong and Xiaohua Zhang and Shaohua Liu and Ruola Ning and Ge Wang},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.01262}
}
X-ray computed tomography (CT) reconstructs cross-sectional images from projection data. However, ionizing X-ray radiation associated with CT scanning might induce cancer and genetic damage. Therefore, the reduction of radiation dose has attracted major attention. Few-view CT image reconstruction is an important topic to reduce the radiation dose. Recently, data-driven algorithms have shown great potential to solve the few-view CT problem. In this paper, we develop a dual network architecture… 

Figures and Tables from this paper

3D Few-View CT Image Reconstruction with Deep Learning
TLDR
This paper proposes a threedimensional (3D) deep-learning-based method for few-view CT image reconstruction directly from 3D projection data that addresses the large memory requirement for reconstructing an image volume directly from cone-beam projection data.
Deep Encoder-Decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-View Data
TLDR
The proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data and can utilize 3D information to produce promising reconstruction results.
Deep Efficient End-to-end Reconstruction (DEER) Network for Low-dose Few-view Breast CT from Projection Data
TLDR
A Deep Efficient End-to-end Reconstruction (DEER) network for low-dose few-view breast CT, validated on a cone-beam breast CT dataset prepared by Koning Corporation on a commercial scanner, demonstrates competitive performance over the state-of-the-art reconstruction networks in terms of image quality.
Deep Efficient End-to-End Reconstruction (DEER) Network for Few-View Breast CT Image Reconstruction
TLDR
A Deep Efficient End-to-end Reconstruction (DEER) network for few-view breast CT image reconstruction that demonstrates a competitive performance over the state-of-the-art reconstruction networks in terms of image quality and low model complexity.
The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review
TLDR
Algorithms using deep learning technology are superior to traditional IR methods in noise suppression, artifact reduction and structure preservation, in terms of improving the image quality of low-dose reconstructed images.
Supervised Transfer Learning at Scale for Medical Imaging
TLDR
Interestingly, it is found that for some of these properties, transfer from natural to medical images is indeed extremely effective, but only when performed at sufficient scale.
Unsupervised Training of Denoisers for Low-Dose CT Reconstruction Without Full-Dose Ground Truth
TLDR
This work attempts to train DNNs for low-dose CT reconstructions with reduced tube current by investigating unsupervised training of DNN's for denoising sensor measurements or sinograms without full-dose ground truth images.
Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data
TLDR
A novel transfer learning approach to overcome the previous drawbacks by means of training the deep learning model on large unlabeled medical image datasets and by next transferring the knowledge to train the deepLearning model on the small amount of labeled medical images is proposed.
Synergizing medical imaging and radiotherapy with deep learning
TLDR
It is believed that deep learning in particular, and artificial intelligence and machine learning in general, will have a revolutionary potential to advance and synergize medical imaging and radiotherapy.
Big Self-Supervised Models Advance Medical Image Classification
TLDR
A novel Multi-Instance Contrastive Learning (MICLe) method that uses multiple images of the underlying pathology per patient case, when available, to construct more informative positive pairs for self-supervised learning is introduced.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
Structurally-Sensitive Multi-Scale Deep Neural Network for Low-Dose CT Denoising
TLDR
This paper proposes a novel 3-D noise reduction method, called structurally sensitive multi-scale generative adversarial net, to improve the low-dose CT image quality, which incorporates3-D volumetric information to improved the image quality.
Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction
TLDR
A deep-neural-network-enabled sinogram synthesis method for sparse-view CT is introduced and its outperformance to the existing interpolation methods and also to the iterative image reconstruction approach is shown.
3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network
TLDR
A conveying path-based convolutional encoder-decoder (CPCE) network in 2-D and 3-D configurations within the GAN framework for LDCT denoising, which has a better performance in that it suppresses image noise and preserves subtle structures.
Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction
TLDR
It is shown that the deep learning approach, combined with the feedback from radiologists, produces higher quality reconstructions than or similar to that using the current commercial methods.
Learning to Reconstruct Computed Tomography Images Directly From Sinogram Data Under A Variety of Data Acquisition Conditions
TLDR
Deep learning method with a common network architecture, termed iCT-Net, was developed and trained to accurately reconstruct images for previously solved and unsolved CT reconstruction problems with high quantitative accuracy, and accurate reconstructions were achieved for the case when the sparse view reconstruction problem is entangled with the classical interior tomographic problems.
LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT
TLDR
This paper unfolds the state-of-the-art “fields of experts”-based iterative reconstruction scheme up to a number of iterations for data-driven training, construct a learned experts’ assessment-based reconstruction network (LEARN) for sparse-data CT, and demonstrates the feasibility and merits of the LEARN network.
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.
Low-dose CT via convolutional neural network.
TLDR
A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion, demonstrating a great potential of the proposed method on artifact reduction and structure preservation.
A Cascaded Convolutional Nerual Network for X-ray Low-dose CT Image Denoising
TLDR
A cascaded training network was proposed in this work, where the trained CNN was applied on the training dataset to initiate new trainings and remove artifacts induced by denoising.
Image Reconstruction is a New Frontier of Machine Learning
TLDR
This special issue focuses on data-driven tomographic reconstruction and covers the whole workflow of medical imaging: from tomographic raw data/features to reconstructed images and then extracted diagnostic features/readings.
...
...