En Es
Categories

Industry News

New AI System Prioritizes Chest X-Rays Containing Critical Findings

By Medimaging International staff writers
07 Feb 2019

Image: Examples of correctly and incorrectly prioritized radiographs. (a) Radiograph was reported as showing large right pleural effusion (arrow). This was correctly prioritized as urgent. (b) Radiograph reported as showing “lucency at the left apex suspicious for pneumothorax.” This was prioritized as normal. On review by three independent radiologists, the radiograph was unanimously considered to be normal. (c) Radiograph reported as showing consolidation projected behind heart (arrow). The finding was missed by the artificial intelligence system, and the study was incorrectly prioritized as normal (Photo courtesy of RSNA).A team of UK researchers has trained an artificial intelligence (AI) system to interpret and prioritize abnormal chest X-rays with critical findings, thereby creating the potential for reducing the backlog of exams and bringing urgently needed care to patients more quickly.

Globally, chest X-rays account for 40% of all diagnostic imaging and the number of exams can create significant backlogs at health care facilities. Deep learning (DL), a type of AI that is capable of being trained to recognize subtle patterns in medical images, is being seen as an automated means to reduce this backlog and identify exams that warrant immediate attention, particularly in publicly funded health care systems.

In their study, the researchers used 470,388 adult chest X-rays to develop an AI system that could identify key findings. The radiologic reports were pre-processed using Natural Language Processing (NLP), an important algorithm of the AI system that extracts labels from written text. For each X-ray, the researchers' in-house system required a list of labels indicating which specific abnormalities were visible on the image.

The NLP analyzed the radiologic report to prioritize each image as critical, urgent, non-urgent or normal. An AI system for computer vision was then trained using labeled X-ray images to predict the clinical priority from appearances only. The researchers tested the system's performance for prioritization in a simulation using an independent set of 15,887 images. The AI system distinguished abnormal from normal chest X-rays with high accuracy. Simulations showed that critical findings received an expert radiologist opinion in 2.7 days, on average, with the AI approach—significantly sooner than the 11.2-day average for actual practice.

"The initial results reported here are exciting as they demonstrate that an AI system can be successfully trained using a very large database of routinely acquired radiologic data," said study co-author Giovanni Montana, Ph.D., formerly of King's College London in London and currently at the University of Warwick in Coventry, England. "With further clinical validation, this technology is expected to reduce a radiologist's workload by a significant amount by detecting all the normal exams so more time can be spent on those requiring more attention."



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

20 Feb 2019
RSNA Debuts New Journal Focused on AI in Radiology
The Radiological Society of North America has published the first issue of its new online journal, Radiology: Artificial Intelligence.
Read More
20 Feb 2019
Researchers Publish Chest X-Ray Dataset to Train AI Models
Researchers from the Stanford University School of Medicine have published CheXpert, a large dataset of chest X-rays and competition for automated chest X-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.
Read More
20 Feb 2019
ECR 2019 Debuts Artificial Intelligence Exhibition
The Artificial Intelligence Exhibition (AIX) made its grand debut at the 2019 European Congress of Radiology (ECR) annual meeting held on Feb. 27-March 3 in Vienna, Austria, bringing AI to the heart of the technical exhibition.
Read More
20 Feb 2019
AI-based Software for Chest X-rays Receives CE Certification
Oxipit, a provider of AI-based medical imaging solutions, has received CE certification for its ChestEye radiology imaging suite.
Read More
20 Feb 2019
Alliance for AI in Healthcare Formally Launched
The Alliance for Artificial Intelligence in Healthcare was formally launched following the inaugural meeting of its 22-person board of directors.
Read More
20 Feb 2019
Global Digital Pathology Market to Reach USD 600 Million by 2022
The global digital pathology market is projected to grow at a CAGR of 8.5% from 2017-2022 to reach USD 600 million by 2022, despite the presence of headwinds that are suppressing market potential and limiting its growth.
Read More
07 Feb 2019
Puritan Medical Products Kicks Off 100th Anniversary Celebrations
Puritan Medical Products Co. LLC, a global manufacturer of single-use products, is all set to celebrate its 100th anniversary this year.
Read More
07 Feb 2019
Global MRI Systems Market to Grow by USD 1.5 Billion in 2019-2023
The global MRI systems market size is projected to grow at a CAGR of more than 5%, or by almost USD 1.58 billion, during the forecast period 2019-2023, driven primarily by technological advances.
Read More
07 Feb 2019
Global In Vitro Diagnostics Market to Reach USD 89 Billion by 2025
The global in vitro diagnostics market was valued at USD 55.00 million in 2016 and is projected to grow at a healthy CAGR of 5.60% between 2017 and 2025 to reach USD 89.8 million by the end of 2025.
Read More
Copyright © 2000-2019 TradeMed.com. All rights reserved. | Terms And Conditions