scholarly journals Comparing image analysis approaches versus expert readers: the relation of knee radiograph features to knee pain

2018 ◽  
Vol 77 (11) ◽  
pp. 1606-1609 ◽  
Author(s):  
Luca Minciullo ◽  
Matthew J Parkes ◽  
David T Felson ◽  
Timothy F Cootes
Keyword(s):  
Image Analysis ◽  
Knee Pain ◽  
Area Under The Curve ◽  
Automated System ◽  
X Rays ◽  
Cross Sectional ◽  
X Ray ◽  
Radiographic Features ◽  
Random Forest Models ◽  
Using Data

ObjectivesThe relationship between radiographic evidence of osteoarthritis and knee pain has been weak. This may be because features that best discriminate knees with pain have not been included in analyses. We tested the correlation between knee pain and radiographic features taking into account both image analysis features and manual scores.MethodsUsing data of the Multicentre Osteoarthritis Study, we tested in a cross-sectional design how well X-ray features discriminated those with frequent knee pain (one question at one time) or consistent frequent knee pain (three questions at three times during the 2 weeks prior to imaging) from those without it. We trained random forest models on features from two radiographic views for classification.ResultsX-rays were better at classifying those with pain using three questions compared with one. When we used all manual radiographic features, the area under the curve (AUC) was 73.9%. Using the best model from automated image analyses or a combination of these and manual grades, no improvement over manual grading was found.ConclusionsX-ray changes of OA are more strongly associated with repeated reports of knee pain than pain reported once. In addition, a fully automated system that assessed features not scored on X-ray performed no better than manual grading of features.

X-ray micro tomography in the scanning electron microscope

1978 ◽  
Vol 36 (1) ◽  
pp. 106-107 ◽  
Author(s):  
W. Brünger
Keyword(s):  
Electron Beam ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Target Surface ◽  
The Body ◽  
X Rays ◽  
Cross Sectional ◽  
X Ray ◽  
Micro Tomography ◽  
Scanning Electron

Reconstructive tomography is a new technique in diagnostic radiology for imaging cross-sectional planes of the human body /1/. A collimated beam of X-rays is scanned through a thin slice of the body and the transmitted intensity is recorded by a detector giving a linear shadow graph or projection (see fig. 1). Many of these projections at different angles are used to reconstruct the body-layer, usually with the aid of a computer. The picture element size of present tomographic scanners is approximately 1.1 mm2.Micro tomography can be realized using the very fine X-ray source generated by the focused electron beam of a scanning electron microscope (see fig. 2). The translation of the X-ray source is done by a line scan of the electron beam on a polished target surface /2/. Projections at different angles are produced by rotating the object.During the registration of a single scan the electron beam is deflected in one direction only, while both deflections are operating in the display tube.

ASSESSMENT OF OSTEOARTHRITIS INITIATIVE–KELLGREN AND LAWRENCE SCORING PROJECTS QUALITY USING COMPUTER ANALYSIS

2010 ◽  
Vol 13 (04) ◽  
pp. 197-201 ◽  
Author(s):  
Lior Shamir ◽  
David T. Felson ◽  
Luigi Ferrucci ◽  
Ilya G. Goldberg
Keyword(s):  
Image Analysis ◽  
Gold Standard ◽  
Population Studies ◽  
Detection Accuracy ◽  
X Rays ◽  
Analysis Method ◽  
Image Analysis Method ◽  
X Ray ◽  
Osteoarthritis Initiative ◽  
Kellgren And Lawrence

The detection of knee osteoarthritis (OA) is a subjective task, and even two highly experienced and well-trained readers might not always agree on a specific case. This problem is noticeable in OA population studies, in which different scoring projects provide significantly different scores for the same knee X-rays. Here we propose a method for quantitative assessment and comparison of knee X-ray scoring projects in OA population studies. The method works by applying an image analysis method that automatically detects OA in knee X-ray images, and comparing the consistency of the scores when using each of the scoring projects as "gold standard." The method was applied to compare the osteoarthritis initiative (OAI) clinic reading derived Kellgren and Lawrence (K&L) scores to central reading, and showed that when using the derived K&L scores the automatic image analysis method was able to accurately differentiate between healthy joints and moderate OA joints in ~70% of the cases. When the OAI central reading scores were used as gold standard, the detection accuracy was elevated to ~77%. These results show that the OAI central readings scores are more consistent with the X-rays, indicating that the central reading better reflects the radiographic features associated with OA, compared to the OAI K&L scores derived from clinic readings.

An investigation into the extent of Lodox imaging usage in South Africa: Radiographer’s perspective

2021 ◽  
Author(s):  
Julius Muchui Thambura ◽  
Jeanette G.E du Plessis ◽  
Cheryl M E McCrindle ◽  
Tanita Cronje
Keyword(s):  
South Africa ◽  
Waiting Times ◽  
Cross Sectional Study ◽  
Trauma Patients ◽  
X Rays ◽  
Online Questionnaire ◽  
Cross Sectional ◽  
Imaging Protocol ◽  
X Ray ◽  
X Ray Imaging

Abstract Introduction Anecdotal evidence suggests that medical professionals in trauma units are requesting additional regional images using conventional x-ray systems, even after trauma patients have undergone full-body Lodox scans. Patients are then exposed to additional radiation, additional waiting times and an increased medical bill. This study aimed at investigating the extent to which Lodox systems were used in trauma units (n=28) in South Africa. Method In this descriptive cross-sectional study, the researcher invited one radiographer from the 28 hospitals in South Africa that use Lodox systems. Radiographers who were most experienced in using the Lodox system completed an online questionnaire. Results Twenty (71.43% n=20) out of twenty-eight radiographers responded. Most hospitals (90%, n=18) were referring patients for additional conventional x-ray images. Radiographers indicated that conventional x-rays were requested for the chest (27.80%, 10/36), the abdomen (16.67%, 6/36), the spine (13.89%, 5/36) and the extremities and skull (19.44%, 7/36). Additionally, radiographers reported using Lodox to perform procedures and examinations usually performed on conventional x-ray systems when conventional x-ray systems were not operational. Conclusion Currently, it is not clear if the use of conventional x-ray imaging following Lodox is necessary, but the results suggest that the practice is commonplace, with healthcare workers in most hospitals (90%, n=18) requesting additional x-ray imaging. The researcher thus recommends that an imaging protocol for Lodox imaging systems should be developed to guide the referral of the patients for further imaging.

An Efficient Method for Coronavirus Detection Through X-rays using deep Neural Network

2021 ◽  
Vol 17 ◽  
Author(s):  
P. Srinivasa Rao ◽  
Pradeep Bheemavarapu ◽  
P. S. Latha Kalyampudi ◽  
T. V. Madhusudhana Rao
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Chronic Respiratory Disease ◽  
Automated System ◽  
X Rays ◽  
Medical Problems ◽  
X Ray ◽  
Chest X Ray ◽  
Fully Connected

Background: Coronavirus (COVID-19) is a group of infectious diseases caused by related viruses called coronaviruses. In humans, the seriousness of infection caused by a coronavirus in the respiratory tract can vary from mild to lethal. A serious illness can be developed in old people and those with underlying medical problems like diabetes, cardiovascular disease, cancer, and chronic respiratory disease. For the diagnosis of the coronavirus disease, due to the growing number of cases, a limited number of test kits for COVID-19 are available in the hospitals. Hence, it is important to implement an automated system as an immediate alternative diagnostic option to pause the spread of COVID-19 in the population. Objective: This paper proposes a deep learning model for classification of coronavirus infected patient detection using chest X-ray radiographs. Methods: A fully connected convolutional neural network model is developed to classify healthy and diseased X-ray radiographs. The proposed neural network model consists of seven convolutional layers with rectified linear unit, softmax (last layer) activation functions and max pooling layers which were trained using the publicly available COVID-19 dataset. Results and Conclusion: For validation of the proposed model, the publicly available chest X-ray radiograph dataset consisting COVID-19 and normal patient’s images were used. Considering the performance of the results that are evaluated based on various evaluation metrics such as precision, recall, MSE, RMSE & accuracy, it is seen that the accuracy of the proposed CNN model is 98.07%.

scholarly journals Computed Tomography- and Radiography-Based Morphometric Analysis of the Lateral Mass of the Subaxial Cervical Spine in the Indian Population

2018 ◽  
Vol 12 (1) ◽  
pp. 18-28
Author(s):  
Nirmal D Patil ◽  
Sudhir K Srivastava ◽  
Sunil Bhosale ◽  
Shaligram Purohit
Keyword(s):  
Computed Tomography ◽  
Cervical Spine ◽  
Indian Population ◽  
Tertiary Care ◽  
X Rays ◽  
Lateral Mass ◽  
Cross Sectional ◽  
X Ray ◽  
Subaxial Cervical Spine ◽  
Screw Length

<sec><title>Study Design</title><p>This was a double-blinded cross-sectional study, which obtained no financial support for the research.</p></sec><sec><title>Purpose</title><p>To obtain a detailed morphometry of the lateral mass of the subaxial cervical spine.</p></sec><sec><title>Overview of Literature</title><p>The literature offers little data on the dimensions of the lateral mass of the subaxial cervical spine.</p></sec><sec><title>Methods</title><p>We assessed axial, sagittal, and coronal computed tomography (CT) cuts and anteroposterior and lateral X-rays of the lateral mass of the subaxial cervical spine of 104 patients (2,080 lateral masses) who presented to a tertiary care public hospital (King Edward Memorial Hospital, Mumbai) in a metropolitan city in India.</p></sec><sec><title>Results</title><p>For a majority of the parameters, males and females significantly differed at all levels (<italic>p</italic>&lt;0.05). Females consistently required higher (<italic>p</italic>&lt;0.05) minimum lateral angulation and lateral angulation. While the minimum lateral angulation followed the order of C5&lt;C4&lt;C6&lt;C3, the lateral angulation followed the order of C3&lt;C5&lt;C4&lt;C6. The lateral mass becomes longer and narrower from C3 to C7. In axial cuts, the dimensions increased from C3 to C6. The sagittal cut thickness and diagonal length increased and the sagittal cut height decreased from C3 to C7. The sagittal cut height was consistently lower in the Indian population at all levels, especially at the C7 level, as compared with the Western population, thereby questioning the acceptance of a 3.5-mm lateral mass screw. A good correlation exists between X-ray- and CT-based assessments of the lateral mass.</p></sec><sec><title>Conclusions</title><p>Larger lateral angulation is required for Indian patients, especially females. The screw length can be effectively calculated by analyzing the lateral X-ray. A CT scan should be reserved for specific indications, and a caution must be exercised while inserting C7 lateral mass screws.</p></sec>

A cohort study using pulmonary function tests and x-ray examination in toner-handling workers

2014 ◽  
Vol 34 (4) ◽  
pp. 345-356 ◽  
Author(s):  
H Kitamura ◽  
N Terunuma ◽  
S Kurosaki ◽  
K Hata ◽  
M Masuda ◽  
...  
Keyword(s):  
Pulmonary Function ◽  
Health Effects ◽  
Pulmonary Function Tests ◽  
Personal Exposure ◽  
Working Environment ◽  
X Rays ◽  
Cross Sectional ◽  
X Ray ◽  
Function Tests ◽  
Chest X Ray

Objectives: This study uses pulmonary function tests and chest x-ray examinations to examine the relationship between toner-handling work and its health effects. Methods: The subjects were 1504 male workers in a Japanese toner and photocopier manufacturing company, in the age range from 19 to 50 years in 2003. Personal exposure measurements, pulmonary function tests, chest x-ray examinations, biomarker measurements, and a questionnaire about respiratory symptoms were conducted. The present study reports the results of pulmonary function tests and chest x-ray examinations conducted in the subjects, which includes a cross-sectional study on the toner handling and non-handling workers and a longitudinal study from 2003 to 2008. Results: Few significant findings were suspected to be caused by toner exposure found in pulmonary function indices in both the cross-sectional and longitudinal studies. Any obvious fibrotic findings in chest x-ray findings related to the toner exposure could not be found out. Conclusion: No evidence of adverse effects on pulmonary function indices and chest x-rays was present in the toner-handling workers as compared to the nonspecifically exposed workers. Although the toner exposure concentration is quite low in the current well-controlled working environment, even among the toner-handling workers, we would like to continue this study in the future to verify the toner exposure health effects.

scholarly journals Automation analysis X-ray of the spine to objectify the assessment of the severity of scoliotic deformity in idiopathic scoliosis: a preliminary report

2020 ◽  
Vol 8 (3) ◽  
pp. 317-326
Author(s):  
Grigory A. Lein ◽  
Natalia S. Nechaeva ◽  
Gulnar М. Mammadova ◽  
Andrey A. Smirnov ◽  
Maxim M. Statsenko
Keyword(s):  
Neural Network ◽  
Idiopathic Scoliosis ◽  
Cobb Angle ◽  
Machine Learning Algorithms ◽  
Automated System ◽  
X Rays ◽  
X Ray ◽  
Scoliotic Deformity ◽  
Window Method ◽  
Treatment Type

Background. A large number of studies have focused on automating the process of measuring the Cobb angle. Although there is no practical tool to assist doctors with estimating the severity of the curvature of the spine and determine the best suitable treatment type. Aim. We aimed to examine the algorithms used for distinguishing vertebral column, vertebrae, and for building a tangent on the X-ray photographs. The superior algorithms should be implemented into the clinical practice as an instrument of automatic analysis of the spine X-rays in scoliosis patients. Materials and methods. A total of 300 digital X-rays of the spine of children with idiopathic scoliosis were gathered. The X-rays were manually ruled by a radiologist to determine the Cobb angle. This data was included into the main dataset used for training and validating the neural network. In addition, the Sliding Window Method algorithm was implemented and compared with the machine learning algorithms, proving it to be vastly superior in the context of this research. Results. This research can serve as the foundation for the future development of an automated system for analyzing spine X-rays. This system allows processing of a large amount of data for achieving 85% in training neural network to determine the Cobb angle. Conclusions. This research is the first step toward the development of a modern innovative product that uses artificial intelligence for distinguishing the different portions of the spine on 2D X-ray images for building the lines required to determine the Cobb angle.

scholarly journals Assessment of size of adenoid-comparison of adenoidal nasopharyngeal ratio and nasal endoscopy in children with chronic adenoiditis

2019 ◽  
Vol 7 (3) ◽  
pp. 776
Author(s):  
Sunaina Binth Hamza ◽  
Ranjith V. T.
Keyword(s):  
Otitis Media ◽  
Otitis Media With Effusion ◽  
Lateral View ◽  
Nasal Endoscopy ◽  
X Rays ◽  
Cross Sectional ◽  
Gold Standard Method ◽  
X Ray ◽  
Grade 3 ◽  
Chronic Adenoiditis

Background: Adenoid hypertrophy (AH) is a common cause of upper airway obstruction in paediatric patients and can have a significant influence on the health of the child. Children who have hypertrophic adenoids often exhibit nasal obstruction, snoring, sleep apnea, otitis media with effusion and craniofacial abnormalities. The main objective of this study was to know the association between size of adenoids and occurrence of otitis media with effusion (OME) and to correlate the grades of AH by lateral nasopharyngeal radiograph and nasal endoscope.Methods: This was an observational cross-sectional study of 100 children who were diagnosed as chronic adenoiditis were studied clinically with relevant investigations. The digital X-ray nasopharynx lateral view and nasal endoscopic results of all the patients were analyzed and graded.Results: Mean Adenoidal-nasopharyngeal ratio for which OME was present was 0.72 which corresponds to X-ray grade 2. It was also found that 80.6% of X-ray grade 3 adenoids had OME and 100% of cases of endoscopic grade 4 adenoids had OME in either or both ears.  36 cases with grade 3 X-rays, 69% were in endoscopic grade 3 and 19.4% cases were shown to have complete choanal obstruction (grade 4).Conclusions: There is significant association between the size of adenoids and OME. The X-ray nasopharynx provides a more convenient method and nasal endoscopy is the gold standard method for determining whether the AH is clinically significant or not.

In Vivo X-Ray Fluorescence of Lead and Other Toxic Trace Elements

1994 ◽  
Vol 38 ◽  
pp. 563-572 ◽  
Author(s):  
David R. Chettle
Keyword(s):  
Blood Lead ◽  
Data Sets ◽  
X Rays ◽  
Cross Sectional ◽  
X Ray ◽  
Fluorescence Measurements ◽  
Bone Lead ◽  
Γ Rays ◽  
Source Excitation

Abstract The first in vivo x-ray fluorescence measurements of lead in bone used y-rays from a 57Co source to excite Pb K x-rays. Later systems used γ-rays from 109Cd to excite Pb K x-rays or polarized x-rays to excite Pb L x-rays. All three approaches involve an extremely low effective dose to the subject. Of the two K x-ray techniques, 109Cd is more precise and more flexible in choice of measurement site. Pb L x-ray fluorescence (L-XRF) effectively samples lead at bone surfaces, whereas Pb K x-ray fluorescence (K-XRF) samples through the bulk of a bone. Both the polarized L-XRF and 109Cd K-XRF achieve similar precision. Renal mercury has recently been determined using a polarized x-ray source. Both renal and hepatic cadmium can be measured using polarized x-rays in conjunction with a Si(Li) detector. Platinum and gold have been measured both by radioisotopic source excitation and by using polarized x-rays, but the latter is to be preferred. Applications of Pb K-XRF have shown that measured bone lead relates strongly to cumulative lead exposure. Secondly, biological half lives of lead in different bone types have been estimated from limited longitudinal data sets and from some cross sectional surveys. Thirdly, the effect of hone lead as an endogenous source of lead has been demonstrated and it has been shown that a majority of circulating blood lead can be mobilized from bone, rather than deriving from new exposure, in some retired lead workers.

scholarly journals Galactic plane structure in hard X-rays

2009 ◽  
Vol 5 (H15) ◽  
pp. 809-809
Author(s):  
A. Lutovinov ◽  
M. Revnivtsev ◽  
R. Krivonos
Keyword(s):  
Energy Band ◽  
Galactic Plane ◽  
Galactic Disk ◽  
X Rays ◽  
X Ray ◽  
The Galaxy ◽  
Increased Sensitivity ◽  
Using Data

AbstractWe study the structure of the Galaxy in the hard X-ray energy band (¿20 keV) using data from the INTEGRAL observatory. The increased sensitivity of the survey and the very deep observations performed during six years of the observatory operation allow us to detect about a hundred new sources. This significantly enlarges the sample of hard X-ray sources in the Galactic disk and bulge in a comparison with the previous studies.

Sign in / Sign up

Export Citation Format

Share Document