A5009633692- High-Energy Particle Collisions Research
- Particle physics theoretical and experimental studies
- Forensic Anthropology and Bioarchaeology Studies
- Quantum Chromodynamics and Particle Interactions
- Bone health and osteoporosis research
- Growth Hormone and Insulin-like Growth Factors
- Autopsy Techniques and Outcomes
- Dental Radiography and Imaging
- Sexual Differentiation and Disorders
- Radiomics and Machine Learning in Medical Imaging
- Spectroscopy and Chemometric Analyses
- Birth, Development, and Health
- Nuclear reactor physics and engineering
- Medical Imaging and Analysis
- Nuclear physics research studies
- Morphological variations and asymmetry
- Fault Detection and Control Systems
- Meat and Animal Product Quality
- Body Composition Measurement Techniques
- Medical Imaging Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- 3D Shape Modeling and Analysis
- Orthopedic Surgery and Rehabilitation
- Spectroscopy Techniques in Biomedical and Chemical Research
- Genetic Associations and Epidemiology
Vetenskap I Skolan
2009-2014
Technical University of Denmark
2002-2003
Danish Meat Trade College
1991-1998
European Organization for Nuclear Research
1988-1993
University of Copenhagen
1986-1988
Institute of Physics
1988
Brookhaven National Laboratory
1988
University of Pittsburgh
1986
Bone age rating is associated with a considerable variability from the human interpretation, and this motivation for presenting new method automated determination of bone (skeletal maturity). The method, called BoneXpert, reconstructs, radiographs hand, borders 15 bones automatically then computes ldquointrinsicrdquo ages each 13 (radius, ulna, 11 short bones). Finally, it transforms intrinsic into Greulich Pyle (GP) or Tanner Whitehouse (TW) age. reconstruction rejects images abnormal...
Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration catalyze AI model creation, identify innovators imaging. Materials Methods goal this challenge solicit individuals teams create algorithm or using ML techniques that would accurately determine skeletal age a curated data set pediatric hand radiographs. primary...
ADVERTISEMENT RETURN TO ISSUEPREVArticleNEXTOptimal minimal neural interpretation of spectraClaus. Borggaard and Hans Henrik. ThodbergCite this: Anal. Chem. 1992, 64, 5, 545–551Publication Date (Print):March 1, 1992Publication History Published online1 May 2002Published inissue 1 March 1992https://pubs.acs.org/doi/10.1021/ac00029a018https://doi.org/10.1021/ac00029a018research-articleACS PublicationsRequest reuse permissionsArticle Views551Altmetric-Citations225LEARN ABOUT THESE...
Abstract The BoneXpert method for automated determination of bone age from hand X-rays was introduced in 2009 and is currently running over 200 hospitals. aim this work to present version 3 the validate its accuracy self-validation mechanism that automatically rejects an image if it at risk being analysed incorrectly. training set included 14,036 images 2017 Radiological Society North America (RSNA) Bone Age Challenge, 1642 normal Dutch Californian children, 8250 Tübingen patients with Short...
The autonomous artificial intelligence (AI) system for bone age rating (BoneXpert) was designed to be used in clinical radiology practice as an AI-replace tool, replacing the radiologist completely.The aim of this study investigate how tool is practice. Are radiologists more inclined use BoneXpert assist rather than replace themselves, and much time saved?We sent a survey consisting eight multiple-choice questions 282 departments Europe already using software.The 97 (34%) respondents came...
Bone age (BA) assessment is a routine procedure in paediatric radiology, for which the Greulich and Pyle (GP) atlas mostly used. There rater variability, but advent of automatic BA determination eliminates this.To validate BoneXpert method skeletal maturity healthy children against manual GP ratings.Two observers determined with knowledge chronological (CA). A total 226 boys 3-17 years 179 girls 3-15 were included study. BoneXpert's estimate was calibrated to agree on average ratings based...
Adult height prediction is a common procedure in pediatric endocrinology, but it associated with considerable variability and bias from the bone age rating.A new method for adult presented, based on automated determination.The predicts fraction of left to grow BoneXpert age. This refined by drawing toward population mean, or alternatively predicted parents' heights. Boys' body mass index girls' at menarche can be included optionally as predictors.A total 231 normal children First Zurich...
Purpose To investigate improvements in performance for automatic bone age estimation that can be gained through model ensembling. Materials and Methods A total of 48 submissions from the 2017 RSNA Pediatric Bone Age Machine Learning Challenge were used. Participants provided with 12 611 pediatric hand radiographs ages determined by a radiologist to develop models determination. The final results using test set 200 labeled weighted average six ratings. mean pairwise correlation all possible...
A technique for constructing neural network architectures with better ability to generalize is presented under the name Ockham's Razor: several networks are trained and then pruned by removing connections one retraining. The which achieve fewest best. method tested on a classification of bit strings (the contiguity problem): optimal architecture emerges, resulting in perfect generalization. internal representation changes substantially during retraining, this distinguishes from previous...
BoneXpert, an automated method for analysis of hand radiographs children, has recently been developed and validated in European children. It determines Tanner-Whitehouse (TW) Greulich Pyle (GP) bone ages (BA). The purpose this work is to validate BoneXpert BA Japanese children determine the following two properties method: (1) accuracy BA, i.e. standard deviation from experienced TW rater. (2) precision BoneXpert's ability yield same value on a repeated radiograph. data consist studies: 185...
The Minimum Description Length (MDL)approach to shape modelling seeks a compact description of set shapes in terms the coordinates marks on shapes. It has been shown that mark positions resulting from this optimisation large extent solve so-called point correspondence problem: How select points defined as curves so correspond across data set. However, MDL approach does not capture important characteristics related curvature curves, and occasionally it places obvious conflict with human...
<i>Background/Aims:</i> A more advanced bone age (BA) has been reported for the left hand relative to right hand, while another study found no such effect. The aim was average difference of automated BoneXpert BA determination (left- vs. right-hand) normal children, examine precision automatic and provide a reference Caucasian children. <i>Methods:</i> Radiographs both hands (age range: 2–20 years) were digitised analysed automatically determine Greulich-Pyle BA,...
Background and aims: Manual bone age (BA) rating in precocious puberty (PP) is associated with considerable rater variability. The aim was to evaluate a new method for automated Greulich Pyle (GP) BA determination children PP.
Rationale and Objective. Large studies have previously been performed to set up a Chinese bone age reference, but it has difficult compare the maturation of children with populations elsewhere due potential variability between raters in different parts world. We re-analysed radiographs from large study normal using an automated rating method establish tempo other populations. Materials Methods. X-rays 2883 boys 3143 girls aged 2-20 years five cities, taken 2005, were evaluated BoneXpert...