En Es
Categories

Industry News

AI Could Learn How to Understand Radiologist Reports

By Medimaging International staff writers
08 Feb 2018

Image: Researchers have taken an important first step in the development of artificial intelligence (AI) that could interpret scans and diagnose conditions (Photo courtesy of iStock).Researchers at the Icahn School of Medicine at Mount Sinai (New York, NY, USA) have used machine learning techniques, including natural language processing algorithms, to identify clinical concepts in radiologist reports for computed tomography (CT) scans. The technology marks an important first step in the development of artificial intelligence (AI) that could interpret scans and diagnose conditions.

AI is expected to help radiologists interpret X-rays, CT scans, and magnetic resonance imaging (MRI) studies, but requires computer software to be "taught" the difference between a normal study and abnormal findings. The researchers conducted a study to train AI technology to understand text reports written by radiologists by creating a series of algorithms to teach the computer clusters of phrases, such as phospholipid, heartburn, and colonoscopy.

Using 96,303 radiologist reports associated with head CT scans performed at The Mount Sinai Hospital and Mount Sinai Queens between 2010 and 2016, the researchers trained the computer software. They calculated metrics that reflected the variety of language used in these reports and compared them to other large collections of text, including thousands of books, Reuters news stories, inpatient physician notes, and Amazon product reviews in order characterize the "lexical complexity" of radiologist reports. The researchers found an accuracy of 91%, demonstrating that it is possible to automatically identify concepts in text from the complex domain of radiology.

"The language used in radiology has a natural structure, which makes it amenable to machine learning," said senior author Eric Oermann, MD, Instructor in the Department of Neurosurgery at the Icahn School of Medicine at Mount Sinai. "Machine learning models built upon massive radiological text datasets can facilitate the training of future AI-based systems for analyzing radiological images."

"The ultimate goal is to create algorithms that help doctors accurately diagnose patients," says first author John Zech, a medical student at the Icahn School of Medicine at Mount Sinai. "Deep learning has many potential applications in radiology -- triaging to identify studies that require immediate evaluation, flagging abnormal parts of cross-sectional imaging for further review, characterizing masses concerning for malignancy -- and those applications will require many labeled training examples."

Related Links:
Icahn School of Medicine at Mount Sinai



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

10 Aug 2018
Global Medical Robots Market to Reach USD 16 Billion by 2023
The global medical robots market is projected to grow at a CAGR of 21.0% from an estimated USD 6.46 billion in 2018 to USD 16.74 billion by 2023, driven by technological advancements, advantages of robot-assisted training in rehabilitation therapy, increased funding for medical robot research, and IPOs issued by medical robot companies. However, safety concerns over robotic surgery devices are expected to limit the market growth to some extent. Recent studies have found a number of technical difficulties and complications experienced while performing procedures using robotic systems. According to the FDA, from 2000 to 2013, surgical robots have been linked to over 144 deaths, over 1,391 injuries, and 8,061 device malfunctions.
Read More
10 Aug 2018
Deep Learning-Based System Detects Lesions in Knee MR Images
Researchers from the department of radiology at the University of Wisconsin School of Medicine and Public Health have developed a deep learning approach to detect cartilage lesions by evaluating MR images of the knee. The researchers used segmentation and classification convolutional neural networks (CNNs) to develop the fully automated deep learning–based cartilage lesion detection system.
Read More
10 Aug 2018
New AI Software Cuts Radiation Therapy Planning Time
Researchers from the University of Toronto have developed automation software that will cut down the time for developing radiation therapy plans — individualized maps that help doctors determine where to blast tumors — from days to mere hours.
Read More
10 Aug 2018
RSNA Announces AI and Machine-Learning Initiatives for 2018
The Radiological Society of North America has planned a diverse roster of machine learning (ML) and artificial intelligence (AI) programming for RSNA 2018 that will focus on the power and potential of AI in radiology and issues associated with implementation.
Read More
10 Aug 2018
Global Market for Machine Learning to Surpass USD 2 Billion by 2023
The global market for machine learning in medical imaging is expected to record a robust growth and surpass USD 2 billion by 2023, driven by benefits such as enhanced productivity, increased diagnostic accuracy, more personalized treatment planning and improved clinical outcomes. However, the market is still in the innovator and early adopter phase, and will need to overcome several barriers before AI becomes mainstream in medical imaging. These are the latest findings of Signify Research, an independent supplier of market intelligence and consultancy to the global healthcare technology industry.
Read More
09 Aug 2018
Stago Connect.One Network Allows Remote Monitoring of Analyzers
Diagnostica Stago, an in-vitro diagnostics company focusing on thrombosis and hemostasis, has launched the secure Connect.One network architecture, which allows laboratories to benefit from remote monitoring of their automated analyzers.
Read More
31 Jul 2018
DIAsource Immunoassays Enters Agreement with ZenTech for RIA Products
DIAsource Immunoassays, a BioVendor group company, has entered into a strategic agreement with ZenTech under which ZenTech will transfer its portfolio of radioimmunoassays (RIA) products to DIAsource, securing their continued production and sales.
Read More
31 Jul 2018
Report Shows Micro-Machined Ultrasound Transducers Market Growing
Micro-machined ultrasonic transducers (MUTs), in the form of PMUTs (Piezoelectric micro-machined ultrasonic transducers) and CMUTs (capacitive micro-machined ultrasonic transducers), are finally coming to market. New applications, along with improved manufacturing capabilities and advanced technological readiness, are driving the impressive growth of MUTs.
Read More
31 Jul 2018
Machine-Learning Algorithm Analyzes Images to Identify Schizophrenia Patients
A team of researchers from the University of Alberta has developed a machine-learning algorithm to examine functional magnetic resonance imaging (fMRI) images for identifying patients suffering from schizophrenia and ascertaining if they would respond to treatment. In a study, the algorithm examined MRI images of both newly diagnosed, previously untreated schizophrenia patients and healthy subjects and successfully identified patients with schizophrenia at 78% accuracy. It also predicted whether or not a patient would respond positively to a specific antipsychotic treatment named risperidone with 82% accuracy.
Read More
Copyright © 2000-2018 TradeMed.com. All rights reserved. | Terms And Conditions