X-ray Generator Research Articles

Development of a chest X-ray machine learning convolutional neural network model on a budget and using artificial intelligence explainability techniques to analyze patterns of machine learning inference.

Machine learning (ML) will have a large impact on medicine and accessibility is important. This study's model was used to explore various concepts including how varying features of a model impacted behavior. This study built an ML model that classified chest X-rays as normal or abnormal by using ResNet50 as a base with transfer learning. A contrast enhancement mechanism was implemented to improve performance. After training with a dataset of publicly available chest radiographs, performance metrics were determined with a test set. The ResNet50 base was substituted with deeper architectures (ResNet101/152) and visualization methods used to help determine patterns of inference. Performance metrics were an accuracy of 79%, recall 69%, precision 96%, and area under the curve of 0.9023. Accuracy improved to 82% and recall to 74% with contrast enhancement. When visualization methods were applied and the ratio of pixels used for inference measured, deeper architectures resulted in the model using larger portions of the image for inference as compared to ResNet50. The model performed on par with many existing models despite consumer-grade hardware and smaller datasets. Individual models vary thus a single model's explainability may not be generalizable. Therefore, this study varied architecture and studied patterns of inference. With deeper ResNet architectures, the machine used larger portions of the image to make decisions. An example using a custom model showed that AI (Artificial Intelligence) can be accessible on consumer-grade hardware, and it also demonstrated an example of studying themes of ML explainability by varying ResNet architectures.

Electron acceleration and x-ray generation from near-critical-density carbon nanotube foams driven by moderately relativistic lasers

Direct laser acceleration of electrons in near-critical-density (NCD) carbon nanotube foams (CNFs) has its advantages in the high-efficiency generation of relativistic electrons and broadband x-rays. Here, we report the first simultaneous measurement on the spectra of laser-driven electrons and x-rays from CNFs at moderately relativistic intensities of around 5×1019 W/cm2. The density and thickness of the CNFs were scanned in the experiments, indicating the optimized electron temperature of 5.5 MeV and x-ray critical energy of 5 keV. Two-dimensional particle-in-cell simulations confirm that the electrons, with a temperature significantly higher than the pondermotive scale, are directly accelerated by the laser along the NCD plasma channel, while the bright x-rays are emitted by these electrons through betatron radiation or Thomson backscattering inside the channel. The simultaneously generated electrons and x-rays, automatically synchronized with the femtosecond laser driver, are suitable for applications such as bi-modal radiography.

Hand-held GPU accelerated device for multiclass classification of X-ray images using CNN model

Chest X-ray (CXR) images are the primary investigation aid for many lung diseases and their follow-ups. For diagnosis of SARS-CoV-2, RT–PCR test and chest Computed Tomography (CT) are commonly used but both face false negatives for ruling out the infection. So, there is a demanding need for developing a system combined with Artificial Intelligence (AI) and CXR imaging to detect COVID-19 patients to avoid its spread. Here, a robust and efficient handheld device is proposed. It uses the computational power of the Graphics Processing Unit (GPU) and pre-trained deep learning models for analyzing the CXR images. A Resnet-50 CNN model is deployed on an NVIDIA Jetson Nano GPU module for the real-time classification of COVID-19, Tuberculosis, and Normal using CXR images. The device can perform real-time classification of CXR images from a portable X-ray machine and classify the image into one of the above categories. For the extensive training, a database of 680 COVID-19, 1230 Tuberculosis, and 1050 normal CXR images are extracted by combining several global databases like Kaggle, SIRM, RSNA, and Radiopaedia. The classification accuracy, precision, and loss rate were 0.9879, 0.9758, and 0.0196 respectively and our model would improve with larger data sets. The highly accurate and high-performance GPU device significantly plays a far-reaching role in COVID-19 diagnosis using Chest X-ray, which could be beneficial to triage the health system and to combat the outbreak of COVID-19.

Synthesis of Iron Copper Sulphide (FeCuS) Thin Film and its Characterization

The Influence of SILAR cycle on the optical, morphological as well as compositional properties of Iron Copper Sulphide (FeCuS) thin film was reported. Utilizing the straightforward and reasonably priced SILAR technique, the deposition was carried out by the use of soda lime glass (SLG) substrates. With a concentration of 1.0M for Iron (Fe) ions, the deposition process was repeated 50, 60, and 70 times, with an 80-seconds dip time per cycle. Morphological characterization of the thin film was analyzed with Scanning Electron Microscopy (SEM) instrument. The compositional properties were analyzed with Energy Dispersive X-Ray machine. A UV-VIS Spectrophotometer was utilized to examine the thin film's optical characteristics. The presence of deposited thin film samples is confirmed by the SEM results, which display higher peaks for the elements Fe, Cu, and S. The results of the EDX analysis demonstrated that an increase in concentration enhances the homogeneity and adhesion of the deposited films in addition to their crystallinity. It was discovered that the thin film's energy band gap for each SILAR cycle was 0.9 eV, 1.3 eV, and 2.99 eV respectively.

Detecting bone lesions in X-ray under diverse acquisition conditions.

The diagnosis of primary bone tumors is challenging as the initial complaints are often non-specific. The early detection of bone cancer is crucial for a favorable prognosis. Incidentally, lesions may be found on radiographs obtained for other reasons. However, these early indications are often missed. We propose an automatic algorithm to detect bone lesions in conventional radiographs to facilitate early diagnosis. Detecting lesions in such radiographs is challenging. First, the prevalence of bone cancer is very low; any method must show high precision to avoid a prohibitive number of false alarms. Second, radiographs taken in health maintenance organizations (HMOs) or emergency departments (EDs) suffer from inherent diversity due to different X-ray machines, technicians, and imaging protocols. This diversity poses a major challenge to any automatic analysis method. We propose training an off-the-shelf object detection algorithm to detect lesions in radiographs. The novelty of our approach stems from a dedicated preprocessing stage that directly addresses the diversity of the data. The preprocessing consists of self-supervised region-of-interest detection using vision transformer (ViT), and a foreground-based histogram equalization for contrast enhancement to relevant regions only. We evaluate our method via a retrospective study that analyzes bone tumors on radiographs acquired from January 2003 to December 2018 under diverse acquisition protocols. Our method obtains 82.43% sensitivity at a 1.5% false-positive rate and surpasses existing preprocessing methods. For lesion detection, our method achieves 82.5% accuracy and an IoU of 0.69. The proposed preprocessing method enables effectively coping with the inherent diversity of radiographs acquired in HMOs and EDs.

Phantom study of a self-shielded X-ray bone age assessment instrument against scattered radiation in children.

Hand-wrist radiography is the most common and accurate method for evaluating children's bone age. To reduce the scattered radiation of radiosensitive organs in bone age assessment, we designed a small X-ray instrument with radioprotection function by adding metal enclosure for X-ray shielding. We used a phantom operator to compare the scattered radiation doses received by sensitive organs under three different protection scenarios (proposed instrument, radiation personal protective equipment, no protection). The proposed instrument showed greater reduction in the mean dose of a single exposure compared with radiation personal protective equipment especially on the left side which was proximal to the X-ray machine (≥80.0% in eye and thyroid, ≥99.9% in breast and gonad). The proposed instrument provides a new pathway towards more convenient and efficient radioprotection.

Estimating of radiation output of X-RAY tube using mathematical model: Case of high-frequency machines

PurposeDuring any radiological procedure, it is important to know the dose to be-administered to the patient and this can be done by estimating the output of the X-ray tube either with a dosimeter or with a mathematical equation or Monte Carlo simulations. The aim of this work is to develop a new mathematical model equation (NMME) for estimating the output of high-frequency X-ray tubes. MethodsTo achieve this, data collected from ten machines in many regions of Cameroon were used (for nine machines) to build an initial model that does not take into account the anode angle and the tenth machine was used to test the model. Using the SpekCalc software, some simulations were carried out to evaluate the influence of the anode angle. This allowed the NMME to be proposed. ResultsThe deviations frequencies between 0.65% and 19.61% were obtained by comparing the output values obtained using initial model with the measured values. The statistical hypothesis test showed that the estimated values using initial model and NMME are in agreement with those measured unlike the Kothan and Tungjai model. For the tenth machine, the percentage difference between estimated and measured values is less than 8 %. ConclusionThese results show that the proposed model performed better than the previous models. In the absence of a dosimeter, the NMME could be used to estimate the output of high frequency X-ray machines and therefore the radiation doses received by patients during diagnostic X-ray examinations.

PErspective and current status of Radiotherapy Service in IRan (PERSIR)-1 study: assessment of current external beam radiotherapy facilities, staff and techniques compared to the international guidelines

Background and purposeRadiotherapy (RT) is an essential treatment modality against cancer and becoming even more in demand due to the anticipated increase in cancer incidence. Due to the rapid development of RT technologies amid financial challenges, we aimed to assess the available RT facilities and the issues with achieving health equity based on current equipment compared to the previous reports from Iran.Materials and methodsA survey arranged by the Iran Cancer Institute's Radiation Oncology Research Center (RORC) was sent to all of the country's radiotherapy centers in 2022. Four components were retrieved: the reimbursement type, equipment, human resources, and patient load. To calculate the radiotherapy utilization rate (RUR), the Lancet Commission was used. The findings were compared with the previous national data.ResultsSeventy-six active radiotherapy centers with 123 Linear accelerators (LINACs) were identified. The centers have been directed in three ways. 10 (20 LINACs), 36 (50 LINACs), and 30 centers (53 LINACs) were charity-, private-, and public-based, respectively. Four provinces had no centers. There was no active intraoperative radiotherapy machine despite its availability in 4 centers. One orthovoltage X-ray machine was active and 14 brachytherapy devices were treating patients. There were 344, 252, and 419 active radiation oncologists, medical physicists, and radiation therapy technologists, respectively. The ratio of LINAC and radiation oncologists to one million populations was 1.68 and 4.10, respectively. Since 2017, 35±5 radiation oncology residents have been trained each year.ConclusionThere has been a notable growth in RT facilities since the previous reports and Iran's situation is currently acceptable among LMICs. However, there is an urgent need to improve the distribution of the RT infrastructure and provide more facilities that can deliver advanced techniques.

First implementation of quality control procedures on selected X-ray machines in South of Benin

Abstract Introduction: The use of X-ray equipment for medical diagnostic radiography procedures has increased due to advances and complexity of radiological procedures. Achieving good image quality while keeping exposure of workers, public and patient exposure to an acceptable level has become a prerequisite for the radiology department in order to comply with best international practices. The aim of this study was to undertake quality control measurement of seven (7) diagnostic radiography equipment in the south of Benin, the first of its kind. Material and methods: Multifunction detector (Piranha) and beam alignment test tool were used to perform quality control tests on seven (7) X-ray units. The method used as well as the interpretation of the results was based on the American Association of Physicists in Medicine (AAPM), United States Food and Drug Administration (FDA), Healing Arts Radiation Protection (HARP), Institute of Physics and Engineering in Medicine (IPEM), International Atomic Energy Agency (IAEA) and Canadian Safety code 35 (S.C 35) recommendations. Results: The quality control results showed that all X-ray equipment investigated were within standard limits for accuracy of exposure time below 10 ms; reproducibility of kVp, exposure time and dose output; specific dose-kVp2 linearity; and specific dose-mAs linearity. Five (5) out of seven (7) diagnostic X-ray machines passed quality control tests such as X-ray beam alignment, exposure time above 10 ms and kVp accuracy. One (1) X-ray machine failed the quality control test of beam filtration at 70 kVp and above. Conclusions: The findings of this study have provided baseline data for other radiology departments to embark on similar QA/QC activities, and also explore options for optimization of patient dose. However, there is a need to extend the study to cover more diagnostic X-ray machines throughout the country. It is anticipated that this would ultimately assist in improving radiation protection and safety during medical diagnostic radiological procedures.

STUDY OF GEOMETRIC UNSHARPNESS PHENOMENON IN WELDED PLATES USING INDUSTRIAL RADIOGRAPHY METHOD

The purpose of this document is to elucidate the methodology employed in analyzing the impact of unsharpness resulting from an X-ray generator on the assessment of steel welded joints. The presence of unsharpness significantly affects the accuracy of welded joint inspections conducted through industrial radiographic techniques, distorting actual measurements of potential discontinuities within the weld. To address this issue, a series of welded joint testing specimens were fabricated using a Shielded Metal Arc Welding (SMAW) process. Each specimen was intentionally designed to contain simulated discontinuities whose dimensions adhered to the acceptance or rejection criteria outlined in the API 1104 standard. Subsequently, radiographic testing was conducted on each specimen, and the dimensions of the simulated discontinuities captured on the radiographic films were measured using the "ISee!" software, as recommended by the ASTM E1165 standard. Upon comparison of the actual and theoretical measurements, it was observed that the maximum unsharpness along the X-axis was recorded in specimens featuring elongated slag inclusions (ESI), with a value of 0.1948 mm. Conversely, the maximum unsharpness along the Y-axis was attributed to individual porosities (P), with a recorded value of 0.1041 mm.

Test measurements of an ASIC for X-ray material discrimination by using on-chip time domain integration and a CdTe sensor

Using time-domain integration (TDI) and a two-dimensional sensor is beneficial for X-ray imaging of moving objects. Applying on-chip instead off-chip TDI decreases the required data throughput between an ASIC and the backend several times [1]. This, in turn, allows us to significantly simplify the ASIC itself as well as the backend.We present the results of test measurements of an ASIC dedicated for X-ray material discrimination by using on-chip TDI and a CdTe sensor.The main part of the ASIC is an 192 × 64 pixel matrix. The pixel size is 100 μm × 100 μm, so the chip size is approximately 6.7 mm × 2 cm. The chip is manufactured in a 130 nm CMOS technology with 8 metal layers. A single pixel analog front-end consists of a charge-sensitive amplifier, a shaper, and three discriminators followed by counters. The test was conducted with a 0.75 mm thick CdTe sensor.First, we show the results of the discriminator offset correction followed by the evaluation of the pixel analog front-end gain and noise conducted with single energy radiation. Next, the results of moving objects imaging are obtained by using an industrial X-ray machine for food inspection (continuous energy spectrum). This is carried out to present an example of the image and evaluate the image signal to noise ratio for different energy discriminator thresholds, sensor bias voltages, detector module temperatures and object speeds.

Observed epochal variations in X-ray lines from the O supergiant ζ Puppis do not require substantial changes in the wind mass flux

ABSTRACT We fit the high-resolution Chandra X-ray spectra of the O supergiant ζ Puppis using the variable boundary condition (VBC) line model to test the stability of its mass-loss rate between two epochs of observation: 2000 March and 2018 July – 2019 August. At issue is whether the observed variations are induced by global changes in the cool (unshocked) wind itself or are isolated to the local pockets of hot gas (i.e. changes in the frequency and location of the shocks). Evidence in the literature favoured the possibility of a 40 per cent increase in the mass flux of the entire stellar wind, based on X-ray reabsorption from a line-deshadowing-instability-inspired parametrization, whereas our fit parameters are consistent with a constant mass flux with a change in the velocity variations that determine the locations where shocks form. Our results suggest the shocks in the more recent data are formed at somewhat larger radii, mimicking the enhanced blueshifts and increased line fluxes interpreted in the previous analysis as being due to increases in both the X-ray generation and reabsorption from an overall stronger wind.

Impact of electrical aging on x-ray image quality and dose rate with vertically aligned carbon nanotube based cold cathode electron beam (C-beam)

The adoption of vertically aligned carbon nanotubes (VACNTs) as electron emitters in x-ray generation has opened a new path for medical imaging technology advancement. With their outstanding electron emission capabilities, VACNTs provide a distinct advantage in miniaturizing and improving the performance of x-ray devices. This research focuses on the effect of electrical aging on x-ray imaging quality and the dose rate while using VACNTs as the electron source. The study includes a thorough examination of the electrical aging effects on VACNT-based x-ray systems, with an emphasis on changes in emission characteristics, beam stability, and the resulting variations in x-ray output. Experiment results show that electrical aging has a considerable impact on the performance of VACNT-based x-ray sources, with visible changes in electron emission parameters and subsequent consequences on x-ray imaging quality. Furthermore, the study investigates the relationship between electrical aging and the x-ray dose rate, providing vital insights into radiation exposure optimization in medical diagnostics.

MULTI-LABEL CLASSIFICATION OF THORACIC DISEASES USING STRUCTURED DEEP LEARNING FRAMEWORK

The current medical scenario indicates that thoracic diseases are the primary cause of illnesses of human beings worldwide. COVID-19 outbreak results in the generation of tremendous Chest X-Ray (CXR) and Computed Tomography (CT) image data archives because CXR and CT imaging are the foremost effective screening tools that characterize patterns and features of pathologies present in the lungs. After careful observation, these chest radiographs show that images are often labeled with more than one pathology, that extends disease diagnosis problem to tedious multi-label classification task. So, this paper proposes a modified mish activation function and compound loss-based Separable Convolution Neural Network (SCNN) model that accomplishes image-level detection of multiple pathologies and COVID-19 from multi-modality chest radiographs. We investigate the power of separable convolution in the CNN network that interprets spatial and depth-wise dimensions of each pixel in CXR and CT images. A modified mish called as Swmish, a non-monotonic activation function, is introduced that preserves negative gradient flow of input and capture fine-grained detail of multiple regions. Moreover, a compound loss function of dice coefficient and binary cross entropy is applied that strongly optimizes the model during training. The generality of the proposed SCNN model is confirmed after conducting comprehensive experiments on multi-label CXR and COVID19-CT datasets. The proposed model gains an AUC score of 0.91 and loss of 0.13 on the multi-label CXR dataset and achieves a testing accuracy of 0.97, AUC score of 0.99 and a loss of 0.11 on the COVID19-CT dataset. These results show that the proposed model achieves highest evaluation metrics in classifying binary and multi-label thoracic abnormalities from multi-modality chest radiographs.

Hematological and Cytogenetic Effects of X-rays in Cardiac Unit Workers and Catheterization Patients.

Introduction X-rays are widely used in medicine for diagnosis and treatment. Such beneficial uses may cause potentially hazardous situations for patients andworkers in the cardiac catheterization laboratory. The present study aims to estimate the radiation dose scattered in different parts of the catheterization units and doses absorbed by workers in thisunit, and patients who underwent cardiac catheterization procedures to evaluate all changes in hematological parameters and damaged cells (the cells that contain a number of chromosomal aberrations) after exposure to radiation at Azadi Teaching Hospital in the Duhok City of Iraq. Methodology Thestudy was conducted in one year and involved 19 male workers chronically exposed to X-ray machines in the cardiac catheterization laboratory, and 45 patients, 20 males and 25 females, who have been exposed to lower doses of X-ray during the cardiac catheterization process. There were 32 healthy individuals, 19 males and 13 females, as a control. Scattered radiation was calculated using an area monitoring detector.Optically Stimulated Luminescence (OSL) dosimeter andFlat Panel Detector (FPD)were used to calculate absorbed doses by workers and patients, respectively. Twelve hematological parameters before and after radiation were examined between study groups; the cytogenetic effects, damagedcells, and chromosomal aberrations of the white blood cells of workers, patientsin the catheterization unit, and individuals of the control group were analyzed. Results The results showed that the scattered X-rays in the catheterization unit after one year of continuous detection did not change significantly compared to the data before the start of the trial. The results of all blood parameters looked to be significantly different (p<0.05) compared to the controls but within the normal range.There is no significant difference (p>0.05) in corpuscular hemoglobin, white blood cells, red distribution width, and neutrophilvalues for workers after one year of exposure as compared with the control. Also, there was no significant difference (p>0.05) in white blood cells, neutrophils, and monocyte values for patients after the operation. The current study showed the damaged cells in workerswere significantlydifferent compared to the control. At the same time, the differences were non-significant for all workers (p=0.0962) after one year of exposure.The differences in damaged cells in patients were highly significant after the operation (p=0.0003). The present study demonstrated that the inductions of dicentrics, acentric, chromosome break, and ring chromosomes in human lymphocytes were intimately related to the irradiation dose. Conclusions The presentstudy found that the scattered X-rays in the catheterization unit after the end of the experiment did not change significantly. The current study also revealed that the exposure to X-rays had no significant effects on the blood indicators of workers and patients in the catheterization unit, whereas the damaged cells in patients did not change significantly compared with the control group at the beginning of the experiment.In patients, these cells were increased after the operation but were present at a high level in the workers, as compared with controls.The damaged cells in workers remained constant from the beginning of the experiment till the end.Finally, patients had increased damaged cells after the end of the trial period compared to workers.

Quality Control of Conventional X-Ray Machine at Najran University Hospital Radiology Department

Quality Control of Conventional X-Ray Machine at Najran University Hospital Radiology Department

Evaluation of Radiological Health Hazard Indices Arising from Diagnostic X-Ray Rooms

The effective dose of selected health care workers who are constantly exposed to X-ray radiation was measured using thermoluminescence dosimeters (TLD) placed over the lead apron at the chest region in all categories of medical personnel investigated. The objective is to conduct radiation measurements in various chosen hospitals to determine the level of exposure from X-ray machines precisely at a distance of 1 meter from the primary source. The work was carried out within a year in each of the selected centers. The personnel examination records containing the type of examination each day, peak tube voltage, tube current, and exposure time, including the actual number of films used, were obtained. A total of 40 personnel were examined in the Government Hospital, Agbor, 21 in Central Hospital Owa Alero and 18 in Okonye Hospital. The method used here has also been used by other researchers. Findings showed that the results obtained from the three hospitals investigated in this work were found to conform with the recommendations of the National Commission on Radiological and Protection {NCRP} 70 and 116 protocols. The Radiologists in the three study areas have the highest dose level, but of particular note is the dosage of the radiologists in Okonye hospital. This, as observed, is because the protective shielding parameters were inadequate and this could result in severe health consequences over time.

TomoRay: Generating Synthetic Computed Tomography of the Spine From Biplanar Radiographs.

Computed tomography (CT) imaging is a cornerstone in the assessment of patients with spinal trauma and in the planning of spinal interventions. However, CT studies are associated with logistical problems, acquisition costs, and radiation exposure. In this proof-of-concept study, the feasibility of generating synthetic spinal CT images using biplanar radiographs was explored. This could expand the potential applications of x-ray machines pre-, post-, and even intraoperatively. A cohort of 209 patients who underwent spinal CT imaging from the VerSe2020 dataset was used to train the algorithm. The model was subsequently evaluated using an internal and external validation set containing 55 from the VerSe2020 dataset and a subset of 56 images from the CTSpine1K dataset, respectively. Digitally reconstructed radiographs served as input for training and evaluation of the 2-dimensional (2D)-to-3-dimentional (3D) generative adversarial model. Model performance was assessed using peak signal to noise ratio (PSNR), structural similarity index (SSIM), and cosine similarity (CS). At external validation, the developed model achieved a PSNR of 21.139 ± 1.018 dB (mean ± standard deviation). The SSIM and CS amounted to 0.947 ± 0.010 and 0.671 ± 0.691, respectively. Generating an artificial 3D output from 2D imaging is challenging, especially for spinal imaging, where x-rays are known to deliver insufficient information frequently. Although the synthetic CT scans derived from our model do not perfectly match their ground truth CT, our proof-of-concept study warrants further exploration of the potential of this technology.

High-Voltage Autonomous Current-Fed Push–Pull Converter With Wireless Communication Applied to X-Ray Generation

High-Voltage Autonomous Current-Fed Push–Pull Converter With Wireless Communication Applied to X-Ray Generation

Operational Challenges in Conducting a Subnational TB Prevalence Survey in India: Lessons Learned for Resource-Limited, High-Burden Settings.

Estimating the burden of TB at the subnational level is critical to planning and prioritizing resources for TB control activities according to the local epidemiological situation. We report the experiences and operational challenges of implementing a TB prevalence survey at the subnational level in India. Information was collected from research reports that gathered data from periodic meetings, informal discussions with study teams, letters of communication, and various site visit reports. During the implementation of the survey, several challenges were encountered, including frequent turnover in human resources, lack of survey participation and community engagement, breakdown of X-ray machines, laboratory issues that delayed sputum sample testing, delays in X-ray reading, and network and Internet connectivity issues that impeded data management. To help ensure the survey was implemented in a timely manner, we developed several solutions, including planning ahead to anticipate challenges, ensuring timely communication, having a high commitment from all stakeholders, having strong team motivation, providing repetitive hands-on training, and involving local leaders to increase community engagement. This experience may help future states and countries that plan to conduct TB prevalence surveys to address these anticipated challenges and develop alternative strategies well in advance.