scholarly journals A Deep Learning-Based Scatter Correction of Simulated X-ray Images

Electronics ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 944 ◽  
Author(s):  
Heesin Lee ◽  
Joonwhoan Lee

X-ray scattering significantly limits image quality. Conventional strategies for scatter reduction based on physical equipment or measurements inevitably increase the dose to improve the image quality. In addition, scatter reduction based on a computational algorithm could take a large amount of time. We propose a deep learning-based scatter correction method, which adopts a convolutional neural network (CNN) for restoration of degraded images. Because it is hard to obtain real data from an X-ray imaging system for training the network, Monte Carlo (MC) simulation was performed to generate the training data. For simulating X-ray images of a human chest, a cone beam CT (CBCT) was designed and modeled as an example. Then, pairs of simulated images, which correspond to scattered and scatter-free images, respectively, were obtained from the model with different doses. The scatter components, calculated by taking the differences of the pairs, were used as targets to train the weight parameters of the CNN. Compared with the MC-based iterative method, the proposed one shows better results in projected images, with as much as 58.5% reduction in root-mean-square error (RMSE), and 18.1% and 3.4% increases in peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM), on average, respectively.

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Yi Sun ◽  
Jianfeng Wang ◽  
Jindou Shi ◽  
Stephen A. Boppart

AbstractPolarization-sensitive optical coherence tomography (PS-OCT) is a high-resolution label-free optical biomedical imaging modality that is sensitive to the microstructural architecture in tissue that gives rise to form birefringence, such as collagen or muscle fibers. To enable polarization sensitivity in an OCT system, however, requires additional hardware and complexity. We developed a deep-learning method to synthesize PS-OCT images by training a generative adversarial network (GAN) on OCT intensity and PS-OCT images. The synthesis accuracy was first evaluated by the structural similarity index (SSIM) between the synthetic and real PS-OCT images. Furthermore, the effectiveness of the computational PS-OCT images was validated by separately training two image classifiers using the real and synthetic PS-OCT images for cancer/normal classification. The similar classification results of the two trained classifiers demonstrate that the predicted PS-OCT images can be potentially used interchangeably in cancer diagnosis applications. In addition, we applied the trained GAN models on OCT images collected from a separate OCT imaging system, and the synthetic PS-OCT images correlate well with the real PS-OCT image collected from the same sample sites using the PS-OCT imaging system. This computational PS-OCT imaging method has the potential to reduce the cost, complexity, and need for hardware-based PS-OCT imaging systems.


2021 ◽  
Vol 13 (19) ◽  
pp. 3859
Author(s):  
Joby M. Prince Czarnecki ◽  
Sathishkumar Samiappan ◽  
Meilun Zhou ◽  
Cary Daniel McCraine ◽  
Louis L. Wasson

The radiometric quality of remotely sensed imagery is crucial for precision agriculture applications because estimations of plant health rely on the underlying quality. Sky conditions, and specifically shadowing from clouds, are critical determinants in the quality of images that can be obtained from low-altitude sensing platforms. In this work, we first compare common deep learning approaches to classify sky conditions with regard to cloud shadows in agricultural fields using a visible spectrum camera. We then develop an artificial-intelligence-based edge computing system to fully automate the classification process. Training data consisting of 100 oblique angle images of the sky were provided to a convolutional neural network and two deep residual neural networks (ResNet18 and ResNet34) to facilitate learning two classes, namely (1) good image quality expected, and (2) degraded image quality expected. The expectation of quality stemmed from the sky condition (i.e., density, coverage, and thickness of clouds) present at the time of the image capture. These networks were tested using a set of 13,000 images. Our results demonstrated that ResNet18 and ResNet34 classifiers produced better classification accuracy when compared to a convolutional neural network classifier. The best overall accuracy was obtained by ResNet34, which was 92% accurate, with a Kappa statistic of 0.77. These results demonstrate a low-cost solution to quality control for future autonomous farming systems that will operate without human intervention and supervision.


1993 ◽  
Vol 306 ◽  
Author(s):  
F. Cerrina ◽  
G.M. Wells

AbstractIn proximity X-ray lithography there is no imaging system in the traditional sense of the word. There are no mirrors, lenses or other means of manipulating the radiation to form an image from that of a pattern (mask). Rather, in proximity X-ray lithography, mask and imaging systems are one and the same. The radiation that illuminates the mask carries the pattern information in the region of the wavefronts that have been attenuated. The detector (photoresist) is placed so close to the mask itself that the image is formed in the region where diffraction has not yet been able to deteriorate the pattern itself. The quality of the image formation then is controlled directly by the interaction between the mask and the radiation field. In turn, this means that both the illumination field and the mask are critical. The properties of the materials used in making the mask thus play a central role in determining the quality of the image. For instance, edge roughness and slope can strongly influence the image by providing the equivalent of a blur in the diffraction process. This blur is beneficial in reducing the high frequency components in the aerial image but it needs to be controlled and be repeatable. The plating (or other physical deposition) process may create variation in density (and thickness) in the deposited film, that will show up as linewidth variation in the image because of local changes in the contrast; the same applies to variations in the carrier membrane. In the case of subtractive process, variations in edge profile across the mask must be minimized.The variations in material composition, thickness and density may all affect the finale image quality; in the case of the resist, local variations in acid concentration may have strong effect in linewidth control (this effect is of course common to all lithographies).Another place where materials will affect the final image quality is in the condensing system. Mirrors will exhibit some degree of surface roughness, leading to a scattered radiation away from the central (coherent) beam. For scanning systems, this is not harmful since no power is lost in the scattering process and a blur is actually created that reduces the degree of spatial coherence. Filters may also exhibit the same roughness; typically it will not affect the image formation. The presence of surface (changes of reflectivity) or bulk (impurities) defects may however strongly alter the uniformity of the transmitted beam. This is particularly true of rolled Be filters and windows, which may include contaminants of high-Z materials. Hence, the grain structure of the window plays a very important role in determining image uniformity.Finally, a seemingly minor but important area is that of the gas used in the exposure area, typically helium. The gas fulfills several needs: heat exchange medium, to thermally clamp the mask to the wafer; low-loss X-ray transmission medium; protection from reactive oxygen radicals and ozone formation. Small amounts of impurities (air) may have a very strong effect on the transmission, and non-uniform distributions are particularly deleterious.All these factors need to be controlled so that the final image is within the required tolerances. Unfortunately, some of these are difficult to characterize in the visible (e.g., reflectivity variations) and testing at X-ray wavelengths is necessary. Although these obstacles are by no means unsurmountable, foresight is necessary in order to deliver a functional X-ray lithography process.This work was supported by various agencies, including ARPA/ONR/NRL and the National Science Foundation.


1998 ◽  
Vol 14 (2) ◽  
pp. 75-83 ◽  
Author(s):  
Yoshiko Ariji ◽  
Jin-ichi Takahashi ◽  
Osamu Matsui ◽  
Tsuneichi Okano ◽  
Munetaka Naitoh ◽  
...  

2012 ◽  
Vol 59 (6) ◽  
pp. 3278-3285 ◽  
Author(s):  
K. Schorner ◽  
M. Goldammer ◽  
K. Stierstorfer ◽  
J. Stephan ◽  
P. Boni

2011 ◽  
Vol 467-469 ◽  
pp. 462-468
Author(s):  
Qi Zhou Wu ◽  
Jing Zhou ◽  
Bin Liu

In X-ray imaging system, with the change of parameters in material quality, volume, object distance and else of the target objects, manual adjustments of tube voltage and tube current are often needed to get ideal imaging results. Whereas human interventions are often subjective that cannot meet the automation development of X-ray detection system. In view of the above problems, a method for objective quality evaluation in images which is based on weighted local entropy is presented in the paper. Parameters adaptive adjustment in X-ray detection system can be based on this method. The validity of the approach is proved by experiment and comparative analysis with the traditional image quality evaluation function.


2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Sorapong Aootaphao ◽  
Saowapak S. Thongvigitmanee ◽  
Jartuwat Rajruangrabin ◽  
Chalinee Thanasupsombat ◽  
Tanapon Srivongsa ◽  
...  

Soft tissue images from portable cone beam computed tomography (CBCT) scanners can be used for diagnosis and detection of tumor, cancer, intracerebral hemorrhage, and so forth. Due to large field of view, X-ray scattering which is the main cause of artifacts degrades image quality, such as cupping artifacts, CT number inaccuracy, and low contrast, especially on soft tissue images. In this work, we propose the X-ray scatter correction method for improving soft tissue images. The X-ray scatter correction scheme to estimate X-ray scatter signals is based on the deconvolution technique using the maximum likelihood estimation maximization (MLEM) method. The scatter kernels are obtained by simulating the PMMA sheet on the Monte Carlo simulation (MCS) software. In the experiment, we used the QRM phantom to quantitatively compare with fan-beam CT (FBCT) data in terms of CT number values, contrast to noise ratio, cupping artifacts, and low contrast detectability. Moreover, the PH3 angiography phantom was also used to mimic human soft tissues in the brain. The reconstructed images with our proposed scatter correction show significant improvement on image quality. Thus the proposed scatter correction technique has high potential to detect soft tissues in the brain.


2010 ◽  
Vol 37 (2) ◽  
pp. 934-946 ◽  
Author(s):  
Hewei Gao ◽  
Rebecca Fahrig ◽  
N. Robert Bennett ◽  
Mingshan Sun ◽  
Josh Star-Lack ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document