A conventional‐to‐spectral CT image translation augmentation workflow for robust contrast injection‐independent organ segmentation

2021 ◽  
Author(s):  
Pierre‐Jean Lartaud ◽  
Claire Dupont ◽  
David Hallé ◽  
Arnaud Schleef ◽  
Riham Dessouky ◽  
...  
Keyword(s):  
Ct Image ◽  
Spectral Ct ◽  
Contrast Injection ◽  
Image Translation

Spectral CT Image Restoration via an Average Image-Induced Nonlocal Means Filter

2016 ◽  
Vol 63 (5) ◽  
pp. 1044-1057 ◽  
Author(s):  
Dong Zeng ◽  
Jing Huang ◽  
Hua Zhang ◽  
Zhaoying Bian ◽  
Shanzhou Niu ◽  
...  
Keyword(s):  
Image Restoration ◽  
Ct Image ◽  
Spectral Ct ◽  
Nonlocal Means ◽  
Average Image

scholarly journals A Novel 3D Reconstruction Algorithm of Motion-Blurred CT Image

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Zhang Jing ◽  
Guo Qiang ◽  
Han Fang ◽  
Li Zhan-Li ◽  
Li Hong-An ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
Signal To Noise Ratio ◽  
Golden Section ◽  
Reconstruction Algorithm ◽  
Spatial Arrangement ◽  
Ct Images ◽  
Normal Vector ◽  
Ct Image ◽  
Clear Image ◽  
Image Translation

The majority of medical workers are eager to obtain realistic and real-time CT 3D reconstruction results. However, autonomous or involuntary motion of patients can cause blurring of CT images. For the 3D reconstruction scene of motion-blurred CT image, this paper consists of two parts: firstly, a GAN image translation network deblurring algorithm is proposed to remove blurred results. This algorithm adopts the clear image to supervise the training process of the blurred image, which creates solutions that are close to the clear image. Secondly, this paper proposes a Marching Cubes (MC) algorithm based on the fusion of golden section and isosurface direction smooth (GI-MC) for 3D reconstruction of CT images. The golden section algorithm is used to calculate the equivalent points and normal vectors, which reduces the calculation numbers from four to one. The isosurface direction smooth algorithm computes the mean value of the normal vector, so as to smooth the direction of all triangular patches in spatial arrangement. The experimental results show that for different blurred angle and blurred amplitude, comparing the results of the Shannon entropy ratio and peak signal-to-noise ratio, our GAN image translation network deblurring algorithm has better restoration than other algorithms. Furthermore, for different types of liver patients, the reconstruction accuracy of our GI-MC algorithm is 9.9%, 7.7%, and 3.9% higher than that of the traditional MC algorithm, Li’s algorithm, and Pratomo’s algorithm, respectively.

MO-FG-204-07: Nonlocal Total Variation Based Spectral CT Image Reconstruction

2015 ◽  
Vol 42 (6Part29) ◽  
pp. 3570-3570 ◽  
Author(s):  
J Liu ◽  
H Ding ◽  
S Molloi ◽  
X Zhang ◽  
H Gao
Keyword(s):  
Image Reconstruction ◽  
Total Variation ◽  
Ct Image ◽  
Spectral Ct ◽  
Nonlocal Total Variation ◽  
Ct Image Reconstruction

scholarly journals Attention-Aware Discrimination for MR-to-CT Image Translation Using Cycle-Consistent Generative Adversarial Networks

2020 ◽  
Vol 2 (2) ◽  
pp. e190027 ◽  
Author(s):  
Vasant Kearney ◽  
Benjamin P. Ziemer ◽  
Alan Perry ◽  
Tianqi Wang ◽  
Jason W. Chan ◽  
...  
Keyword(s):  
Generative Adversarial Networks ◽  
Ct Image ◽  
Adversarial Networks ◽  
Image Translation

scholarly journals Deep Learning-Based Identification of Spinal Metastasis in Lung Cancer Using Spectral CT Images

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Xiaojie Fan ◽  
Xiaoyu Zhang ◽  
Zibo Zhang ◽  
Yifang Jiang
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Detection Rate ◽  
Learning Algorithm ◽  
Spinal Metastasis ◽  
Ct Images ◽  
Ct Image ◽  
Spectral Ct ◽  
Deep Learning Algorithm ◽  
Noise Ratio

In this study, deep learning algorithm-based energy/spectral computed tomography (CT) for the spinal metastasis from lung cancer was used. A dilated convolutional U-Net model (DC-U-Net model) was first proposed, which was used to segment the energy/spectral CT image of patients with the spinal metastasis from lung cancer. Subsequently, energy/spectral CT images under different energy levels were collected for the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) comparison. It was found the learning rate of the model decreased exponentially as the number of training increased, with the lung contour segmented out of the image. Under 40–65 keV, the CT value of bone metastasis from lung cancer decreased with increasing energy, as with the average rank sum test result. The SNR and CNR values were the highest under 60 keV. The detection rate of the deep learning algorithm below 60 keV was 81.41%, and that of professional doctors was 77.56%. The detection rate of the deep learning algorithm below 140 keV was 66.03%, and that of professional doctors was 64.74%. In conclusion, the DC-U-Net model demonstrates better segmentation effects versus the convolutional neutral networ k (CNN), with the lung contour segmented. Further, a higher energy level leads to worse segmentation effects on the energy/spectral CT image.

scholarly journals Tensor decomposition and non-local means based spectral CT image denoising

2019 ◽  
Vol 27 (3) ◽  
pp. 397-416 ◽  
Author(s):  
Yanbo Zhang ◽  
Morteza Salehjahromi ◽  
Hengyong Yu
Keyword(s):  
Image Denoising ◽  
Tensor Decomposition ◽  
Ct Image ◽  
Spectral Ct ◽  
Local Means ◽  
Non Local

Design and calibration of an IVEM for general 3-dimensional imaging of non-diffracting materials

1992 ◽  
Vol 50 (2) ◽  
pp. 1040-1041
Author(s):  
Neil Rowlands ◽  
Jeff Price ◽  
Michael Kersker ◽  
Seichi Suzuki ◽  
Steve Young ◽  
...  
Keyword(s):  
3D Imaging ◽  
Tomographic Reconstruction ◽  
Three Dimensional ◽  
3 Dimensional ◽  
3D Microstructure ◽  
Image Translation ◽  
Digital Correlation ◽  
On Line ◽  
Mechanical Stage ◽  
Projection Angle

Three-dimensional (3D) microstructure visualization on the electron microscope requires that the sample be tilted to different positions to collect a series of projections. This tilting should be performed rapidly for on-line stereo viewing and precisely for off-line tomographic reconstruction. Usually a projection series is collected using mechanical stage tilt alone. The stereo pairs must be viewed off-line and the 60 to 120 tomographic projections must be aligned with fiduciary markers or digital correlation methods. The delay in viewing stereo pairs and the alignment problems in tomographic reconstruction could be eliminated or improved by tilting the beam if such tilt could be accomplished without image translation.A microscope capable of beam tilt with simultaneous image shift to eliminate tilt-induced translation has been investigated for 3D imaging of thick (1 μm) biologic specimens. By tilting the beam above and through the specimen and bringing it back below the specimen, a brightfield image with a projection angle corresponding to the beam tilt angle can be recorded (Fig. 1a).

Sign in / Sign up

Export Citation Format

Share Document