Quality Improvement of X-ray CT Images by Estimation of the Mechanical Misalignment in a Projection Image Using an Iterative Method

2017 ◽  
Vol 137 (3) ◽  
pp. 213-219
Author(s):  
Kenji Noguchi ◽  
Satoshi Takahashi ◽  
Daisuke Suzuki ◽  
Atsushi Teramoto
Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4595
Author(s):  
Parisa Asadi ◽  
Lauren E. Beckingham

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.


2021 ◽  
Vol 11 (9) ◽  
pp. 4233
Author(s):  
Biprodip Pal ◽  
Debashis Gupta ◽  
Md. Rashed-Al-Mahfuz ◽  
Salem A. Alyami ◽  
Mohammad Ali Moni

The COVID-19 pandemic requires the rapid isolation of infected patients. Thus, high-sensitivity radiology images could be a key technique to diagnose patients besides the polymerase chain reaction approach. Deep learning algorithms are proposed in several studies to detect COVID-19 symptoms due to the success in chest radiography image classification, cost efficiency, lack of expert radiologists, and the need for faster processing in the pandemic area. Most of the promising algorithms proposed in different studies are based on pre-trained deep learning models. Such open-source models and lack of variation in the radiology image-capturing environment make the diagnosis system vulnerable to adversarial attacks such as fast gradient sign method (FGSM) attack. This study therefore explored the potential vulnerability of pre-trained convolutional neural network algorithms to the FGSM attack in terms of two frequently used models, VGG16 and Inception-v3. Firstly, we developed two transfer learning models for X-ray and CT image-based COVID-19 classification and analyzed the performance extensively in terms of accuracy, precision, recall, and AUC. Secondly, our study illustrates that misclassification can occur with a very minor perturbation magnitude, such as 0.009 and 0.003 for the FGSM attack in these models for X-ray and CT images, respectively, without any effect on the visual perceptibility of the perturbation. In addition, we demonstrated that successful FGSM attack can decrease the classification performance to 16.67% and 55.56% for X-ray images, as well as 36% and 40% in the case of CT images for VGG16 and Inception-v3, respectively, without any human-recognizable perturbation effects in the adversarial images. Finally, we analyzed that correct class probability of any test image which is supposed to be 1, can drop for both considered models and with increased perturbation; it can drop to 0.24 and 0.17 for the VGG16 model in cases of X-ray and CT images, respectively. Thus, despite the need for data sharing and automated diagnosis, practical deployment of such program requires more robustness.


1990 ◽  
Vol 5 (3) ◽  
pp. 121-124 ◽  
Author(s):  
David J. Devlin ◽  
Kamal E. Amin

AbstractThe relative intensities ratios for the determination of the relative amounts of alpha and beta phases in silicon nitride and the relative amounts of delta yttrium disilicate (Y2Si2O7) and nitrogen apatite [Y5(SiO4)3N] are reported. These constants were determined using an iterative method applicable when the pure phases are not easily prepared. In addition, a calibration curve was obtained for the quantitative measurement of free silicon in silicon nitride over the range 0 to 0.3% by weight of Si.


2021 ◽  
pp. 61-63
Author(s):  
Bharath. V ◽  
Hemanth Kumar ◽  
Ashwanth Narayan ◽  
Venkatachalam .K ◽  
Ashwin. VY ◽  
...  

The Inter-Pedicular and Inter-Pars distance was measured in a plain AP radiography (X-Ray) of 150 and 75 CT images normal patients between 18- 47 years of age. The aim of the study is to measure the normal Inter-Pedicular and Inter-Pars distance. We found that by studying the anatomical relationship between the inner or medial Pedicular border and the Pars outer or lateral border, gives the Orthopaedic Surgeon a reproducible and consistent guide towards exacting a pedicular screw placing. We found that both X-Ray and CT images shows steady increase in the Ipr and Ipd from L1 to L5, there is a minimal difference from L1-L2 and marked difference seen from L3 to L5, and showing the differences in distances are more in the males, compared to females. The Means of all the groups compared also proves that there is steady raise in the diameter of the IPR and IPD from L1 to L5, where there is dramatical and signicant change in the upward direction, noted from L3 to L5. The mean difference is almost constant from L1to L2. So this study, did essentially to help, establish that, the inner medial border of pedicle, is in near relationship to, the outer lateral border of the Pars-Interarticularis, which helps in establishing the latero-medial entry point for the pedicular screw insertion in the lumbar spine.


2021 ◽  
Author(s):  
Khalid Labib Alsamadony ◽  
Ertugrul Umut Yildirim ◽  
Guenther Glatz ◽  
Umair bin Waheed ◽  
Sherif M. Hanafy

Abstract Computed tomography (CT) is an important tool to characterize rock samples allowing quantification of physical properties in 3D and 4D. The accuracy of a property delineated from CT data is strongly correlated with the CT image quality. In general, high-quality, lower noise CT Images mandate greater exposure times. With increasing exposure time, however, more wear is put on the X-Ray tube and longer cooldown periods are required, inevitably limiting the temporal resolution of the particular phenomena under investigation. In this work, we propose a deep convolutional neural network (DCNN) based approach to improve the quality of images collected during reduced exposure time scans. First, we convolve long exposure time images from medical CT scanner with a blur kernel to mimic the degradation caused because of reduced exposure time scanning. Subsequently, utilizing the high- and low-quality scan stacks, we train a DCNN. The trained network enables us to restore any low-quality scan for which high-quality reference is not available. Furthermore, we investigate several factors affecting the DCNN performance such as the number of training images, transfer learning strategies, and loss functions. The results indicate that the number of training images is an important factor since the predictive capability of the DCNN improves as the number of training images increases. We illustrate, however, that the requirement for a large training dataset can be reduced by exploiting transfer learning. In addition, training the DCNN on mean squared error (MSE) as a loss function outperforms both mean absolute error (MAE) and Peak signal-to-noise ratio (PSNR) loss functions with respect to image quality metrics. The presented approach enables the prediction of high-quality images from low exposure CT images. Consequently, this allows for continued scanning without the need for X-Ray tube to cool down, thereby maximizing the temporal resolution. This is of particular value for any core flood experiment seeking to capture the underlying dynamics.


2014 ◽  
Vol 721 ◽  
pp. 783-787
Author(s):  
Shao Hu Peng ◽  
Hyun Do Nam ◽  
Yan Fen Gan ◽  
Xiao Hu

Automatic segmentation of the line-like regions plays a very important role in the automatic recognition system, such as automatic cracks recognition in X-ray images, automatic vessels segmentation in CT images. In order to automatically segment line-like regions in the X-ray/CT images, this paper presents a robust line filter based on the local gray level variation and multiscale analysis. The proposed line filter makes usage of the local gray level and its local variation to enhance line-like regions in the X-ray/CT image, which can well overcome the problems of the image noises and non-uniform intensity of the images. For detecting various sizes of line-like regions, an image pyramid is constructed based on different neighboring distances, which enables the proposed filter to analyze different sizes of regions independently. Experimental results showed that the proposed line filter can well segment various sizes of line-like regions in the X-ray/CT images, which are with image noises and non-uniform intensity problems.


2014 ◽  
Author(s):  
Joshua K. Y. Swee ◽  
Clare Sheridan ◽  
Elza de Bruin ◽  
Julian Downward ◽  
Francois Lassailly ◽  
...  

2002 ◽  
Author(s):  
Toshiharu Ezoe ◽  
Hotaka Takizawa ◽  
Shinji Yamamoto ◽  
Akinobu Shimizu ◽  
Tohru Matsumoto ◽  
...  

Author(s):  
T. Hayashi ◽  
H. Chen ◽  
K. Miyamoto ◽  
X. Zhou ◽  
T. Hara ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document