News | Digital Radiography (DR) | January 23, 2019

Artificial Intelligence Shows Potential for Triaging Chest X-rays

Use of deep learning and natural language processing reduces time to review of critical findings from 11.2 to 2.7 days

 Artificial Intelligence Shows Potential for Triaging Chest X-rays

January 23, 2019 — An artificial intelligence (AI) system can interpret and prioritize abnormal chest X-rays with critical findings, according to a study appearing in the journal Radiology.1 This could potentially reduce the backlog of exams and bringing urgently needed care to patients more quickly.

Chest X-rays account for 40 percent of all diagnostic imaging worldwide. The number of exams can create significant backlogs at healthcare facilities. In the U.K. there are an estimated 330,000 X-rays at any given time that have been waiting more than 30 days for a report.

"Currently there are no systematic and automated ways to triage chest X-rays and bring those with critical and urgent findings to the top of the reporting pile," 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.

Deep learning (DL), a type of AI capable of being trained to recognize subtle patterns in medical images, has been proposed as an automated means to reduce this backlog and identify exams that merit immediate attention, particularly in publicly-funded healthcare systems.

For the study, Montana and colleagues used 470,388 adult chest X-rays to develop an AI system that could identify key findings. The images had been stripped of any identifying information to protect patient privacy. The radiologic reports were pre-processed using natural language processing (NLP), an 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 goes well beyond pattern matching," Montana said. "It uses AI techniques to infer the structure of each written sentence; for instance, it identifies the presence of clinical findings and body locations and their relationships. The development of the NLP system for labeling chest X-rays at scale was a critical milestone in our study."

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," Montana said. "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."

The researchers plan to expand their research to a much larger sample size and deploy more complex algorithms for better performance. Future research goals include a multi-center study to prospectively assess the performance of the triaging software.

"A major milestone for this research will consist in the automated generation of sentences describing the radiologic abnormalities seen in the images," Montana said. "This seems an achievable objective given the current AI technology."

For more information: www.pubs.rsna.org/journal/radiology

Reference

1. Annarumma M., Withey S.J., Bakewell R.J., et al. Automated Triaging of Adult Chest Radiographs with Deep Artificial Neural Networks. Radiology, Jan. 22, 2019. https://doi.org/10.1148/radiol.2018180921

Related Content

ADHD Medication May Affect Brain Development in Children

Images of regions of interest (colored lines) in the white matter skeleton representation. Data from left and right anterior thalamic radiation (ATR) were averaged. Image courtesy of C. Bouziane et al.

News | Neuro Imaging | August 16, 2019
A drug used to treat attention-deficit/hyperactivity disorder (ADHD) appears to affect development of the brain’s...
First Patient Enrolled in World's Largest Brain Cancer Clinical Trial
News | Radiation Therapy | August 15, 2019
Henry Ford Cancer Institute is first-in-the-world to enroll a glioblastoma patient in the GBM AGILE Trial (Adaptive...
Efficacy of Isoray's Cesium Blu Showcased in Recent Studies
News | Brachytherapy Systems | August 14, 2019
August 14, 2019 — Isoray announced a trio of studies recently reported at scientific meetings and published in medica
Imago Systems Announces Collaboration With Mayo Clinic for Breast Imaging

Image courtesy of Imago Systems

News | Mammography | August 14, 2019
Image visualization company Imago Systems announced it has signed a know-how license with Mayo Clinic. The multi-year...
Artificial Intelligence Could Yield More Accurate Breast Cancer Diagnoses
News | Artificial Intelligence | August 13, 2019
University of California Los Angeles (UCLA) researchers have developed an artificial intelligence (AI) system that...
Videos | Radiographic Fluoroscopy (RF) | August 09, 2019
Shimadzu displayed the FluoroSpeed X1 conventional radiographic fluoroscopy (RF) system at the Association for Medica
Shimadzu Medical Systems Receives FDA 510(k) for FluoroSpeed X1 RF System
Technology | Radiographic Fluoroscopy (RF) | August 09, 2019
Shimadzu Medical Systems USA, a subsidiary of Shimadzu Corp., announced they have received U.S. Food and Drug...
Half of Hospital Decision Makers Plan to Invest in AI by 2021
News | Artificial Intelligence | August 08, 2019
August 8, 2019 — A recent study conducted by Olive AI explores how hospital leaders are responding to the imperative
Contrast Use in First Transthoracic Echocardiogram for Heart Failure Reduces Repeat Testing
News | Cardiovascular Ultrasound | August 07, 2019
Heart failure is the fourth most common cause for all admission to U.S. hospitals, and it is the most common reason for...