(Press-News.org) OAK BROOK, Ill. - An automated system that uses artificial intelligence (AI) is effective at detecting a common type of wrist fracture on X-rays, according to a study published in the journal Radiology: Artificial Intelligence. Researchers said the AI-derived algorithm could help speed diagnosis and allow earlier treatment.
Scaphoid fractures are injuries to one of the small bones of the wrist that typically occur when people try to break a fall with their hands. They comprise up to 7% of all skeletal fractures. Prompt diagnosis is important, as the fracture may fail to heal properly if untreated, leading to a host of problems like arthritis and even loss of function.
Conventional X-ray is the imaging technique of choice for diagnosing scaphoid fractures, but it is often limited by overlap of the scaphoid with the surrounding bones of the wrist. Variations in wrist positioning and X-ray technique can also limit the visibility of fractures.
"Consequently, scaphoid fractures can be overlooked during initial X-ray examinations," said study lead author Nils Hendrix, a Ph.D. candidate at the Jeroen Bosch Hospital and Jheronimus Academy of Data Science in the Netherlands.
Hendrix and colleagues recently studied a system that could aid radiologists in detecting these common fractures. The system is based on deep learning with a convolutional neural network, a sophisticated type of AI that is capable of discerning subtle patterns in images beyond the capabilities of the human eye.
While previous research found that a convolutional neural network was inferior to human observers at identifying scaphoid fractures on X-rays, the new study used larger datasets and further algorithm refinements to improve detection. It also employed class activation maps, which are AI tools that help users understand what region of the image is influencing the network's predictions.
The researchers used thousands of conventional X-rays of the hand, wrist and scaphoid to develop the system. They tested it on a dataset of 190 X-rays and compared its performance to that of 11 radiologists.
The system had a sensitivity of 78% for detecting fractures with a positive predictive value of 83%, which refers to the likelihood that patients the AI identifies as having a fracture really do have one. Analysis showed that the system performed comparably to the 11 radiologists.
The system has significant potential in clinical use, Hendrix said. It could reduce the incidence and costs of additional imaging exams and unnecessary therapy, speed up diagnosis and allow earlier treatment.
"The system may be able to assist residents, radiologists or other physicians by acting either as a first or second reader, or as a triage tool that helps prioritize worklists, potentially reducing the risk of missing a fracture," Hendrix said.
Such assistance could prevent delayed therapy and reduce complications that may lead to a subpar clinical outcome, according to Hendrix.
"The convolutional neural network may also reduce unnecessary wrist immobilization, performed out of precaution, in more than half of the patients with clinical suspicion for having a scaphoid fracture," he said.
The class activation maps were found to overlap with fracture lines in the scaphoid, suggesting they could be used for localizing potential fractures.
Hendrix and colleagues plan to expand the scaphoid fracture detection system so that it can combine multiple X-ray views for its predictions. They are also conducting an experimental study in which radiologists are asked to identify scaphoid fractures on X-rays with and without the aid of the fracture detection system.
The researchers hope to extend the system to fracture detection in other bone structures.
INFORMATION:
"Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs." Collaborating with Nils Hendrix were Ernst Scholten, M.D., Ph.D., Bastiaan Vernhout, M.D., Stefan Bruijnen, M.D., Ph.D., Bas Maresch, M.D., Mathijn de Jong, M.D., Suzanne Diepstraten, M.D., Stijn Bollen, M.D., Steven Schalekamp, M.D., Maarten de Rooij, M.D., Ph.D., Alexander Scholtens, M.D., Ward Hendrix, M.Sc., Tijs Samson, M.Sc., Lee-Ling Sharon Ong, Ph.D., Eric Postma, Ph.D., Bram van Ginneken, Ph.D., and Matthieu Rutten, M.D., Ph.D.
Radiology: Artificial Intelligence is edited by Charles E. Kahn Jr., M.D., M.S., Perelman School of Medicine at the University of Pennsylvania, and owned and published by the Radiological Society of North America, Inc. (https://pubs.rsna.org/journal/ai)
RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Illinois. (RSNA.org)
For information on X-rays, visit RadiologyInfo.org.
Studying the violent collisions of black holes and neutron stars may soon provide a new measurement of the Universe's expansion rate, helping to resolve a long-standing dispute, suggests a new simulation study led by researchers at UCL (University College London).
Our two current best ways of estimating the Universe's rate of expansion - measuring the brightness and speed of pulsating and exploding stars, and looking at fluctuations in radiation from the early Universe - give very different answers, suggesting our theory of the Universe may be wrong.
A third type of measurement, looking at the explosions of light and ripples in the fabric of space caused ...
Under the background of global warming, the energy budget of the earth is out of balance with more than 90% of additional heat entering the ocean.
The tropical Pacific Ocean has an important influence on the global tropical climate and the climate of China, and the tropical Pacific Western Boundary Currents (WBCs) that flow through it plays an important role in the climate system. Large-scale ocean circulation redistributes ocean heat and mass and is hence one of the basic dynamic processes that shape the earth's Marine environment. The tropical Pacific WBCs system is a key part of the global ocean circulation system. ...
It is challenging to analyze proteins at low concentrations, especially for those in a mixture of various conformations such as intrinsically disordered proteins (IDPs). A research team led by Prof. HUANG Jinqing, Assistant Professor of Department of Chemistry at The Hong Kong University of Science and Technology (HKUST), has developed optical tweezers-coupled Raman spectroscopy that can directly probe the structural features of alpha-synuclein, an IDP closely linked to Parkinson's disease, at the physiological concentration by focusing on individual protein molecules.
IDPs play an important role in biological processes and many of them are associated with incurable neurodegenerative ...
Researchers from the Universities of Bristol and Surrey have found that well-fitting, three-layered cloth masks can be as effective at reducing the transmission of COVID-19 as surgical masks.
At the height of the COVID-19 pandemic, 139 countries mandated the use of face coverings in public space such as supermarkets and public transports. The World Health Organization also advises the use of face coverings and offers guidance on their effective features. Face coverings suppress the onward transmission of COVID-19 through exhalation and protect the wearer on inhalation.
In a paper published by the Physics of Fluids journal, the researchers detail how they looked at how liquid ...
Areas in Sweden with early access to electricity at the start of the 1900s underwent rapid change. Electrification led to more strikes, but it was not those who were threatened by the new technology who protested. Instead, it was the professional groups who had acquired a stronger negotiating position - thanks to technological development, according to new research from Lund University.
Labour market conditions are affected by new technology. Currently, the impact of automation on the labour market is often discussed, whether jobs will disappear as computers take over, or whether digitalisation drives development towards a gig economy with uncertain employment conditions. One fear is that the technological development could generate social unrest and a risk of increased ...
Like a chameleon of the night sky, the Moon often changes its appearance. It might look larger, brighter or redder, for example, due to its phases, its position in the solar system or smoke in Earth's atmosphere. (It is not made of green cheese, however.)
Another factor in its appearance is the size and shape of moon dust particles, the small rock grains that cover the moon's surface. Researchers at the National Institute of Standards and Technology (NIST) are now measuring tinier moon dust particles than ever before, a step toward more precisely explaining the Moon's apparent color ...
Researchers from the University of Copenhagen, in collaboration with their Swiss colleagues at the University Hospital of Bern, have cracked the code for controlling a group of enzymes that affect our metabolism.
The researchers' findings could help us avoid diseases ranging from high cholesterol to infertility to certain types of cancer, which are all due, among other things, to hormonal imbalances.
They have found a way to influence a special protein called cytochrome P450 reductase (POR) -- popularly characterized as the 'conductor' of the body's protein orchestra, which helps regulate our hormones and makes it possible to break down medicinal products in the liver.
"We have developed a method to ...
Fast growth of the global human population has long been regarded as a major challenge that faces mankind. Presently, this challenge is becoming even more serious than before, in particular because many natural resources are estimated to deplete before the end of this century.
The increasing population pressure on agriculture and ecosystems and the environment more generally is predicted to result in worldwide food and water shortages, pollution, lack of housing, poverty and social tension. The situation is exacerbated by global climate change as considerable areas of land are predicted to be flooded and hence taken out of human's use.
It is widely believed ...
According to the researchers, three songs from a playlist are enough to identify the person who chose the songs. Hence, companies like YouTube and Spotify can accumulate a great deal of information about their users based only on their musical preferences.
The study was led by Dr. Ori Leshman of the Jaime and Joan Constantiner School of Education at Tel Aviv University and Dr. Ron Hirschprung of the Department of Management and Industrial Engineering at Ariel University. The study was published in the journal Telematics and Informatics.
The study included ...
PITTSBURGH, April 28, 2021 - Asthma exacerbations rose following a catastrophic Christmas Eve fire two years ago that destroyed pollution controls at the Clairton Coke Works--the largest such facility in the nation, a University of Pittsburgh Graduate School of Public Health analysis concludes.
The study, published in the Journal of Allergy and Clinical Immunology, was possible because of a collaboration with the University of Pittsburgh Asthma and Environmental Lung Health Institute at UPMC and the Allegheny County Health Department, with funding from The Heinz Endowments.
"In addition to verifying that people living within a 10-mile radius of the coke works had higher rates of asthma exacerbations and use of albuterol rescue medication than those living outside the radius, we learned ...
