Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network

By Hu Chen, Yi Zhang, Mannudeep K. Kalra, Feng Lin, Yang Chen, Peixi Liao, Jiliu Zhou, Ge Wang. IEEE Transactions on Medical Imaging, 2017

1,621 citations recorded by the source corpus.

Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data, whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder–decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Especially, our method has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/603bb905322c80725dab75b4343a78325c662d66

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution (2018, methodology): “The image reconstruction for sparse-view CT has also been investigated with RED-CNN, which is based on the combination of deconvolution network and shortcut connections [4].”
3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network (2018, positive): “Importantly, the proposed strategy is expected to be applicable to all existing 2D models, such as those discussed in [5], [6], [8], [9].”
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss (2017, methodology): “In the future, we plan to incorporate the WGANVGG network with more complicated generators such as the networks reported in [26] and [27] and extend these networks for image reconstruction from raw data by making a neural network counterpart of the FBP process.”
Low-dose CT image and projection dataset (2020, methodology): “A residual encoder–decoder convolutional neural network (RED-CNN) for 2D and 3D CT denoising.(26,27)”
MedGAN: Medical Image Translation using GANs (2018, methodology): “In this section, the diﬀerent loss components and network architecture of MedGAN will be presented starting ﬁrst with some preliminary information.”
LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT (2017, neutral): “was similar to that described in [41], and the blank scan factor b0 was set from 4 × 107 to 1 × 105 with step of 1 × 105.”
Deep learning with convolutional neural network in radiology (2018, positive): “reported that quality of CT images could be improved in terms of qualitative and quanti‐ tative analyses with less time by using models based on deep learning techniques [71, 72].”
Deep Learning in Neuroradiology (2018, methodology): “This has already been applied to CT imaging and has been demonstrated to be of value on a dataset consisting of normal-dose and simulated low-dose CT. 15 Another approach uses paired MR images of the same anatomy, which are acquired at different field strengths.”
Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network (2017, methodology): “We compared the proposed method with the other denoising algorithms such as BM3D [46], MBIR regularized by total variation (TV), ALOHA [47], the image domain deep learning approach (RED-CNN) [14], and CNN with GAN loss [21].”
Secure and Robust Machine Learning for Healthcare: A Survey (2020, methodology): “models is drastically increasing and various DL models such as CNNs [54] and autoencoders [6] have been extensively used for the reconstruction of MRI and CT images.”
CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction (2017, methodology): “These methods generally use the CNN to denoise the sinogram [37] or the reconstruction obtained from a standard technique [16], [38]–[40]; as such, they do not perform the reconstruction directly.”