Enhancing Wire Simulation Accuracy Through X-ray Imaging and Deformation Analysis

Automated staging of knee osteoarthritis severity using deep neural networks

To study the effect of hydraulically induced damage in a caprock (argillite from Tournemire), hydraulic fracturing tests were conducted in a hollow cylinder triaxial cell on core samples with inner borehole, oriented parallel to the bedding plans. Acoustic Emission (AE) monitoring and strain measurements during hydraulic fracturing tests, as well as post-mortem X-ray CT analysis were carried out. Samples were subjected to stresses representative of the in-situ stress state, and different injection rates of low-viscosity fluid (water) were tested.Overall, the breakdown pressure is higher and AE activity due to microcracking damage (which increases almost simultaneously with the pressure drop) appears earlier when the injection flow rate increases. During the second injection phase, peak pressures are lower, pressurization rates are higher and stress-strain behaviour is stiffer. The analysis of values of Rise Angle (RA) and Average Frequency (A-FR) indicates that increasing the injection flow rate generates more tensile cracks and increases the severity of damage. The cumulative damage variable, calculated from AE activity, increases significantly just before the first pressure drop and this increase is stiffer when the injection flow rate increases. This confirms that the use of a low-viscosity fluid (water) induces the propagation of unstable cracks, which initiate almost simultaneously with the pressure drop in the borehole, and that this propagation is faster for higher injection rates.The breakdown pressure and the crack orientation are analysed thanks to the elastic theory for transverse isotropic materials and chemo-hydro-mechanical coupled processes at the borehole wall. The analysis of core samples deformations and X-ray images, and post-mortem visual observation of samples surface indicate that cracks are primarily oriented parallel to the bedding planes and the core sample axis.

The impact analysis of deep learning models for COVID-19-infected X-ray images is an extremely challenging task. Every model has unique capabilities that can provide suitable solutions for some given problem. The prescribed work analyzes various deep learning models that are used for capturing the chest X-ray images. Their performance-defining factors, such as accuracy, f1-score, training and the validation loss, are tested with the support of the training dataset. These deep learning models are multi-layered architectures. These parameters fluctuate based on the behavior of these layers, learning rate, training efficiency, or over-fitting of models. This may in turn introduce sudden changes in the values of training accuracy, testing accuracy, loss or validation loss, f1-score, etc. Some models produce linear responses with respect to the training and testing data, such as Xception, but most of the models provide a variation of these parameters either in the accuracy or the loss functions. The prescribed work performs detailed experimental analysis of deep learning image neural network models and compares them with the above said parameters with detailed analysis of these parameters with their responses regarding accuracy and loss functions. This work also analyses the suitability of these model based on the various parameters, such as the accuracy and loss functions to various applications. This prescribed work also lists out various challenges on the implementation and experimentation of these models. Solutions are provided for enhancing the performance of these deep learning models. The deep learning models that are used in the prescribed work are Resnet, VGG16, Resnet with VGG, Inception V3, Xception with transfer learning, and CNN. The model is trained with more than 1500 images of the chest-X-ray data and tested with around 132 samples of the X-ray image dataset. The prescribed work analyzes the accuracy, f1-score, recall, and precision of these models and analyzes these parameters. It also measures parameters such as training accuracy, testing accuracy, loss, and validation loss. Each epoch of every model is recorded to measure the changes in these parameters during the experimental analysis. The prescribed work provides insight for future research through various challenges and research findings with future directions.

The quality and interpretability of the state-of-the-art methods for automatic analysis of chest X-ray images is still not sufficient. We address this problem by presenting a model that combines the analysis of frontal chest X-ray scans with structured patient information contained within radiology records. The proposed model generates a short textual summary with essential information on the found pathologies along with their location and severity; and the 2D heatmaps localizing each pathology on the original X-ray images. We test the proposed model on the MIMIC-CXR dataset. It achieves the state-of-the-art performance for image labelling and captioning (78.5% of correctly generated sentences) and defeats other similar solutions that dismiss the additional patient data (by 5.2% of correctly generated sentences). We also propose an automatic approach to label mining that leverages multimodal data: the X-ray images, related textual reports, patients' age and sex.

In the domain of AI-driven healthcare, deep learning models have markedly advanced pneumonia diagnosis through X-ray image analysis, thus indicating a significant stride in the efficacy of medical decision systems. This paper presents a novel approach utilizing a deep convolutional neural network that effectively amalgamates the strengths of EfficientNetB0 and DenseNet121, and it is enhanced by a suite of attention mechanisms for refined pneumonia image classification. Leveraging pre-trained models, our network employs multi-head, self-attention modules for meticulous feature extraction from X-ray images. The model’s integration and processing efficiency are further augmented by a channel-attention-based feature fusion strategy, one that is complemented by a residual block and an attention-augmented feature enhancement and dynamic pooling strategy. Our used dataset, which comprises a comprehensive collection of chest X-ray images, represents both healthy individuals and those affected by pneumonia, and it serves as the foundation for this research. This study delves deep into the algorithms, architectural details, and operational intricacies of the proposed model. The empirical outcomes of our model are noteworthy, with an exceptional performance marked by an accuracy of 95.19%, a precision of 98.38%, a recall of 93.84%, an F1 score of 96.06%, a specificity of 97.43%, and an AUC of 0.9564 on the test dataset. These results not only affirm the model’s high diagnostic accuracy, but also highlight its promising potential for real-world clinical deployment.

The application of chest X-ray imaging for early disease screening is attracting interest from the computer vision and deep learning community. To date, various deep learning models have been applied in X-ray image analysis. However, models perform inconsistently depending on the dataset. In this paper, we consider each individual model as a medical doctor. We then propose a doctor consultation-inspired method that fuses multiple models. In particular, we consider both early and late fusion mechanisms for consultation. The early fusion mechanism combines the deep learned features from multiple models, whereas the late fusion method combines the confidence scores of all individual models. Experiments on two X-ray imaging datasets demonstrate the superiority of the proposed method relative to baseline. The experimental results also show that early consultation consistently outperforms the late consultation mechanism in both benchmark datasets. In particular, the early doctor consultation-inspired model outperforms all individual models by a large margin, i.e., 3.03 and 1.86 in terms of accuracy in the UIT COVID-19 and chest X-ray datasets, respectively.

SummaryThe coronavirus (Covid‐19) epidemic continues to have a negative influence on the global population's well‐being and health. Scientists in many fields around the world are working non‐stop to find a solution to the prevention of this epidemic. In the field of computer science, this struggle is supported by studies on especially the analysis of X‐ray and CT images with artificial intelligence. In this study, two different ensemble learning models, including deep learning and a combination of machine learning methods, are presented for the detection of SARS‐CoV‐2 infection from X‐ray images. The main purpose of this study is to increase the classification ability of Residual Convolutional Neural Network (ResCNN), which is used as a deep learning method, with the assist of machine learning algorithms and extracted features from images. The proposed models were validated on a total of 5228 chest X‐ray images categorized as Normal, Pneumonia, and Covid‐19. The images in the dataset were sized in four different ways, 32 × 32, 64 × 64, 128 × 128, and 256 × 256, in order to analyze the validity of the proposed models in more detail. These four datasets were partitioned with the 10‐fold cross‐validation technique and converted into a total of 40 training and test data. Both proposed models use features derived from the ResCNN as the basis and test a certain number of machine learning algorithms with a majority voting technique by dividing them into subsets. In the architecture of the second model, it combines the features extracted from the Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG) methods in addition to the features obtained from the ResCNN. It has been seen that the classification ability of both proposed models is better than the ResCNN in the experiments. In particular, the second model gives a similar classification score even though it is tested with images four‐times smaller (e.g., 32 × 32 vs. 128 × 128) than those used in the ResCNN. This shows that the model can give ideal results with lower computational cost.

X-ray imaging technology has been used for decades in clinical tasks to reveal the internal condition of different organs, and in recent years, it has become more common in other areas such as industry, security, and geography. The recent development of computer vision and machine learning techniques has also made it easier to automatically process X-ray images and several machine learning-based object (anomaly) detection, classification, and segmentation methods have been recently employed in X-ray image analysis. Due to the high potential of deep learning in related image processing applications, it has been used in most of the studies. This survey reviews the recent research on using computer vision and machine learning for X-ray analysis in industrial production and security applications and covers the applications, techniques, evaluation metrics, datasets, and performance comparison of those techniques on publicly available datasets. We also highlight some drawbacks in the published research and give recommendations for future research in computer vision-based X-ray analysis.

Density is an important coal property that determines the potential of gas resources in CBM reservoir. This paper aims to investigate coal density and structure variation during primary CBM and CO2-ECBM experiments. A coal core sample from Alberta Mannville formation with the rank of SubB was used to conduct the core flooding experiments covering the stages of inert gas flow, methane production, methane displacement by CO2 and inert gas flow after CO2 desorption. The x-ray CT experiments were carried out parallel to the core flooding experiment to provide x-ray images of coal core saturated with different gases at different stress conditions. The x-ray techniques were used for visualization and mapping of larger fractures and mineral streaks, as well as identification of flow paths. The coal density and density distribution changed with the gas adsorptive capacity and the stress condition were obtained. The results show that net stress, gas adsorption capacity, and the production history are all key factors affecting coal core structure, leading coal density and density distribution variations. Hence, the core flow path, which contributes to the coal permeability, changes with those factors during CBM/ECBM processes. The results from this study provide laboratory coal characterization techniques using x-ray imaging analysis. Introduction Coalbed methane (CBM) is a new energy source and has the potential to contribute a significant portion of Canadian natural gas production. Coal reservoir characterization is one of the important steps to successfully develop CBM reservoirs. Coal seams are heterogeneous in terms of lithotypes and morphologies. This creates a challenge in understanding the subsurface behavior of the coal and injected gas during primary and enhanced gas recovery processes. As an organic rock, coal structure is easily deformed by the net stress imposed on it. Besides, adsorption of gases causes the coal matrix to swell and desorption of gases causes the coal matrix to shrink(1, 2). Therefore, coal experiences many changes in stress conditions uring the production life of the CBM reservoir. Because the network of natural fractures and cleats in a coal determines to a large extent the mechanical properties of the coal. Coal is very soft and has low elastic modulus compared to the rock formation. The stress and time dependent deformation of the coal porous structure is expected to change the behavior of the most important properties of the coal, such as porosity and permeability, which in turn change the reservoir production profiles. Coal physical properties such as density are therefore dynamically changed with the coal structure deformation. Coal bulk densities are highly useful for determination of the ash content of the coal. Because of the excellent correlation between core ash and gas content and the excellent correlation between core ash and open-hole bulk density data, it is possible to accurately estimate the gas content from the high resolution bulk density log data(3). Coal bulk density is also used in the estimation of the total gas content in a given drainage area(4).

Safety and efficacy of in vitro generated bone-like material for in vivo bone regeneration – a feasibility study

In this case study, the author describes the investigation of a defective DC-DC converter retrieved from an aircraft following the report of abnormal system behavior. Electrical testing, local probing, X-ray imaging, and cross-sectional analysis led to the discovery of cracks on several pins and in some of the solder material. The cracks were caused by different rates of thermal expansion and were remedied with the help of thermomechanical analysis, EBSD imaging, and phase map comparisons for thick and thin solder joints.

Fluid Catalytic Cracking (FCC) catalyst particles are complex, hierarchical, multi-component systems that are used ubiquitously for the production of valuable hydrocarbons such as gasoline and propylene from crude oil feedstocks. In the FCC unit, high heat, steam and feedstocks contaminated with deleterious metals, such as Fe, Ni and V contribute to FCC catalyst deactivation and loss in activity. Due to the broad industrial relevance, there are large economic and societal incentives towards mitigating activity loss and increasing catalyst stability. However, due to their complex chemical nature, study of FCC deactivation remains challenging and requires the use of advanced characterization techniques offering both high resolution and high chemical sensitivity. In this thesis we have employed a range of synchrotron-based X-ray spectromicroscopy techniques in 2-D and 3-D in order to understand the specific mechanisms of FCC catalyst deactivation at the single particle level with unprecedented sensitivity. We describe both the advancements made in X-ray imaging and data analysis therein as well as the insights into catalyst deactivation.

After a worker was found fatally pinned between the top rail of a scissor lift and an overhead beam, rescue attempts were frustrated by unresponsive lift controls. In the investigation of this fatal accident, certain lift controls did not function or functioned intermittently. The intermittent nature of the malfunction indicated that the evidence was sensitive — likely to be disturbed if the device was disassembled using typical destructive techniques. Therefore, nondestructive techniques were required. This study discusses how X-ray imaging, computed tomography (CT), electrical testing, and engineering analysis of the lift and control system were used to investigate the causes and contributing factors of this fatal accident without disturbing sensitive evidence.

Dark-field microscopy is a background-free imaging method that provides high sensitivity and a large signal-to-noise ratio. It finds application in nanoscale detection, biophysics and biosensing, particle tracking, single molecule spectroscopy, X-ray imaging, and failure analysis of materials. In dark-field microscopy, the unscattered light path is typically excluded from the angular range of signal detection. This restriction reduces the numerical aperture and affects the resolution. Here we introduce a nonlinear dark-field scheme that overcomes this restriction. Two laser beams of frequencies ω1 and ω2 are used to illuminate a sample surface and to generate a purely evanescent field at the four-wave mixing (4WM) frequency ω4wm = 2ω1 - ω2. The evanescent 4WM field scatters at sample features and generates radiation that is detected by standard far-field optics. This nonlinear dark-field scheme works with samples of any material and is compatible with applications ranging from biological imaging to failure analysis.

Abstract: The X-ray test is a simple, fast, non-destructive, and highly precise test that enables detailed examination of internal seed morphology and identification of seed damage and its location and type. The objective of the present study was to evaluate the efficiency of the X-ray test and the relationship between the structure of Crotalaria juncea seeds and germination. Six lots of Crotalaria juncea seeds of the IAC-KR1 cultivar were subjected to X-ray and germination tests. Normal and abnormal seedlings and dead seeds were photographed and analyzed together with the X-ray images of the seeds. Results showed that analysis of X-ray images is effective in identifying mechanical damage, stink bug damage, and deteriorated tissues in Crotalaria juncea seeds and is able to establish an association between their occurrence and germination.