GE Healthcare launches new AI suite to detect chest X-ray abnormalities

Collaboration with Lunit quickly analyses chest X-ray findings and flags abnormalities including pneumonia, which may be indicative of COVID-19

The launch of GE Healthcare's Thoracic Care Suite will help to analyse chest X-ray findings and flag abnormalities for review

GE Healthcare’s Thoracic Care Suite harnesses the power of AI to scan for eight chest X-ray abnormalities, including pneumonia indicative of COVID-19 – a key cause of mortality in patients who contract coronavirus.

The AI suite, featuring Lunit Insight CXR, also includes an algorithm to detect tuberculosis, which affects approximately 10 million people every year.

A collection of eight artificial intelligence (AI) algorithms from Lunit Insight CXR, the suite helps to alleviate clinical strain due to COVID-19.

It quickly analyses chest X-ray findings and flags abnormalities to radiologists for review, including pneumonia, which may be indicative of COVID-19 as well as tuberculosis, lung nodules, and other radiological findings.

“The launch of our Thoracic Care Suite is a part of GE Healthcare’s larger effort to help ensure clinicians and partners on the front lines have the equipment they need to quickly diagnose and effectively treat COVID-19 patients,” said Kieran Murphy, president and chief executive of GE Healthcare.”

Clinicians are looking for clinically-proven methods to help identify symptoms early and determine which patients are at higher risk of complications and need to be actively monitored

“The pandemic has proven that data, analytics, AI and connectivity will only become more central to delivering care.

“For GE Healthcare, that means continuing to advance intelligent health and providing innovative technologies. This new offering is the latest example of how X-ray and AI can uphold the highest standard of patient care amid the most-modern of disease threats.”

To date, more than eight million cases of COVID-19 have been confirmed worldwide – overwhelming radiologists, technologists, and physicians.

As the spread of the virus stabilises, clinicians continue to need tools to help manage new cases and complications caused by the virus – including pneumonia and acute respiratory distress – which have further increased pressure on radiologists to quickly read chest X-ray exams.

With approximately 1.44 billion chest X-ray exams taking place each year, radiologists are overwhelmed, especially as they may be looking for multiple indications per exam.

The Thoracic Care Suite harnesses the power of AI to help alleviate these pressures by automatically analysing images for the presence of eight abnormal radiologic findings, including suspected tuberculosis and pneumonia findings, which can be indicative of COVID-19.

Upon reading the flagged report in picture archiving and communication systems (PACS), radiologists can quickly find the abnormality score for each of the eight possible abnormalities, an image overlay, and a written location description to help expedite diagnosis and treatment.

“Clinicians are looking for clinically-proven methods to help identify symptoms early and determine which patients are at higher risk of complications and need to be actively monitored,” explains Professor Fergus Gleeson, consultant radiologist and professor of radiology at the University of Oxford, and the 2020 President of the European Society of Thoracic Imaging.

“AI can help identify these distinctions and enable hospital resources to be targeted to those that will need them while in hospital and following discharge.”

The Thoracic Care Suite provides much-needed support to help quickly identify high-risk cases as well as monitor patients showing the progression and regression of mild respiratory symptoms.

With 97-99% accuracy rate (Area Under the Curve - AUC), the powerful algorithms behind the AI suite have been trained to detect radiologic findings within seconds. In one study, results showed a 34% reduction in reading time per case.

The launch of our Thoracic Care Suite is a part of GE Healthcare’s larger effort to help ensure clinicians and partners on the front lines have the equipment they need to quickly diagnose and effectively treat COVID-19 patients

In addition to detecting pneumonia, Thoracic Care Suite also supports tuberculosis, atelectasis, calcification, cardiomegaly, fibrosis, mediastinal widening, lung nodule, and pleural effusion detection.

Thoracic Care Suite is available to GE Healthcare’s global fixed, mobile and R&F X-ray customers at point of sale, meaning the technology can more quickly be deployed in market and in hospital without annual fees – an important consideration if a second wave of COVID-19 were to occur.

Furthermore, installation of the technology does not require customers to engage with any enterprise IT projects, helping to lower the barrier for entry in adopting AI.

“To have our AI made available with a market-leading vendor like GE Healthcare – especially as part of the Thoracic Care Suite – is a significant advancement in delivering solutions to various customers within GE Healthcare’s install base and bringing us all one step closer to embracing AI as a part of today’s standard of care,” says Brandon Suh, chief executive of Lunit.

Lunit, based in South Korea, is a software company that develops AI-powered analysis of lung diseases via chest X-ray images.

The collaboration with GE Healthcare is one of the first of its kind to bring commercially-available AI products from a medical AI start-up to an existing X-ray equipment manufacturer.

Companies