Self-Supervised Training For Low Dose CT Reconstruction
TLDR
It is demonstrated that this method outperforms both conventional and compressed sensing based iterative reconstruction methods qualitatively and quantitatively in the reconstruction of analytic CT phantoms and real-world CT images in low-dose CT reconstruction task.Abstract:
Ionizing radiation has been the biggest concern in CT imaging. To reduce the dose level without compromising the image quality, low-dose CT reconstruction has been offered with the availability of compressed sensing based reconstruction methods. Recently, data-driven methods got attention with the rise of deep learning, the availability of high computational power, and big datasets. Deep learning based methods have also been used in low-dose CT reconstruction problem in different manners. Usually, the success of these methods depends on labeled data. However, recent studies showed that training can be achieved successfully with noisy datasets. In this study, we defined a training scheme to use low-dose sinograms as their own training targets. We applied the self-supervision principle in the projection domain where the noise is element-wise independent which is a requirement for self-supervised training methods. Using the self-supervised training, the filtering part of the FBP method and the parameters of a denoiser neural network are optimized. We demonstrate that our method outperforms both conventional and compressed sensing based iterative reconstruction methods qualitatively and quantitatively in the reconstruction of analytic CT phantoms and real-world CT images in low-dose CT reconstruction task.read more
Citations
More filters
Journal ArticleDOI
Self-Supervised Noise Reduction in Low-Dose Cone Beam Computed Tomography (CBCT) Using the Randomly Dropped Projection Strategy
TL;DR: Wang et al. as mentioned in this paper proposed a noise reduction method based on the dropped projection strategy, which works by first reconstructing the 3D image with the degraded versions of the projection images generated by Bernoulli sampling.
Peer Review
Systematic Review on Learning-based Spectral CT
Alexandre Bousse,V. S. S. Kandarpa,Simon Rit,Alessandro Perelli,Mengzhou Li,Guobao Wang,Jian Zhou,Ge Wang +7 more
TL;DR: In this article , the authors present the state-of-the-art data-driven techniques for spectral computed tomography (CT) and compare them with the traditional single-energy CT.
Journal ArticleDOI
Self-supervised Physics-based Denoising for Computed Tomography
TL;DR: In this paper , a self-supervised approach for CT denoising is proposed, which can be trained without the high-dose CT projection ground truth images, and achieves state-of-the-art performance.
Journal ArticleDOI
Multi-frame-based Cross-domain Image Denoising for Low-dose Computed Tomography
TL;DR: In this paper , a two-stage learning-based method for low-dose computed tomography (LDCT) denoising was proposed for the commercially available third-generation multi-slice spiral CT scanners.
Proceedings ArticleDOI
Low-Dose Computed Tomography Reconstruction without Learning Data: Performance Improvement by Exploiting Joint Correlation Between Adjacent Slices
TL;DR: The proposed prior adaptation to simultaneously reconstruct multiple adjacent CT slices allows the network to implicitly learn spatial correlation information between slices, consequently improving performance and eliminating noise via inter-slice attention in the wavelet high-frequency region.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Journal ArticleDOI
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
TL;DR: An algorithm based on an enhanced sparse representation in transform domain based on a specially developed collaborative Wiener filtering achieves state-of-the-art denoising performance in terms of both peak signal-to-noise ratio and subjective visual quality.
Journal ArticleDOI
Deep Convolutional Neural Network for Inverse Problems in Imaging
TL;DR: In this paper, the authors proposed a deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems, which combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure.
Journal ArticleDOI
Simultaneous algebraic reconstruction technique (SART): a superior implementation of the art algorithm.
TL;DR: This implementation of the Algebraic Reconstruction Technique appears to have a computational advantage over the more traditional implementation of ART and potential applications include image reconstruction in conjunction with ray tracing for ultrasound and microwave tomography.
Journal ArticleDOI
Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network
TL;DR: 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.
Related Papers (5)
Low dose CT reconstruction assisted by an image manifold prior
Ma Guoyang,Chenyang Shen,Xun Jia +2 more