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

he U.S. Food and Drug Administration (FDA) has issued a final order to reclassify medical image analyzers applied to mammography breast cancer, ultrasound breast lesions, radiograph lung nodules and radiograph dental caries detection, postamendments class III devices (regulated under product code MYN), into class II (special controls), subject to premarket notification

Image courtesy of iCAD

News | Computer-Aided Detection Software | January 22, 2020
January 22, 2020 — The U.S.
Medical imaging technology company Oxipit announced partnership with Swiss medical distribution company Healthcare Konnect to bring ChestEye AI imaging suite to healthcare institutions in Nigeria
News | Artificial Intelligence | January 22, 2020
January 22, 2020 — Medical imaging technology company Oxipit ann
Hitachi Healthcare Americas announced that it will create a new dedicated research and development facility within its North American headquarters facility in Twinsburg, Ohio
News | Radiology Business | January 21, 2020
January 21, 2020 — Hitachi Healthcare Americas announced that it will create a new dedicated research and development
Virtual reality during chemotherapy has been shown to improve breast cancer patients’ quality of life during the most stressful treatments
News | Virtual and Augmented Reality | January 21, 2020
January 21, 2020 — Virtual reality during chemotherapy has been shown to improve...
This is a lung X-ray reviewed automatically by artificial intelligence (AI) to identify a collapsed lung (pneumothorax) in the color coded area. This AI app from Lunit is awaiting final FDA review and in planned to be integrated into several vendors' mobile digital radiography (DR) systems. Fujifilm showed this software integrated as a work-in-progress into its mobile X-ray system at RSNA 2019. GE Healthcare has its own version of this software for its mobile r=ray systems that gained FDA in 2019.   #RSNA #

This is a lung X-ray reviewed automatically by artificial intelligence (AI) to identify a collapsed lung (pneumothorax) in the color coded area. This AI app from Lunit is awaiting final FDA review and in planned to be integrated into several vendors' mobile digital radiography (DR) systems. Fujifilm showed this software integrated as a work-in-progress into its mobile X-ray system at RSNA 2019. GE Healthcare has its own version of this software for its mobile r=ray systems that gained FDA in 2019.

Feature | RSNA | January 20, 2020 | Dave Fornell, Editor
Here are images of some of the newest new medical imaging technologies displayed on the expo floor at the ...
Researchers at Karolinska Institutet in Sweden and Tampere University in Finland have developed a method based on artificial intelligence (AI) for histopathological diagnosis and grading of prostate cancer

From left: Peter Ström, Martin Eklund, Kimmo Kartasalo, Henrik Olsson och Lars Egevad, researchers at Karolinska Institutet in Sweden. Photo courtesy of Stefan Zimmerman

News | Prostate Cancer | January 20, 2020
January 20, 2020 — Researchers at Karolinska Institutet in Sweden and...
Nanox secures $26M supported by strategic investment from Foxconn, unveiling the Startek-inspired AI Biobed for early detection
News | X-Ray | January 16, 2020
January 16, 2020 — Nanox, an innovative medical imaging techn
Carestream’s X-ray digital tomosynthesis functionality creates three-dimensional datasets from digital radiography (DR) that can be scrolled through similar to computed tomography (CT) imaging. It received 510(k) clearance from the U.S. Food and Drug Administration (FDA) in January 2020. Digital tomosynthesis uses a single sweep of X-ray exposures and streamlines operator workflow by separating the process of DT exposure acquisition from image volume formation.
News | Digital Radiography (DR) | January 15, 2020
January 15, 2020 — Carestream’s X-ray digital tomosynthesis (DT) functionality, which creates three-dimensional datas