MedImaging

Download Mobile App
Recent News Radiography MRI Ultrasound Nuclear Medicine General/Advanced Imaging Imaging IT Industry News

AI Suite Detects Most Common Chest X-Ray Findings

By MedImaging International staff writers
Posted on 05 Oct 2021
Print article
Image: Insight CXR detects abnormalities on a chest X-ray image (Photo courtesy of Lunit)
Image: Insight CXR detects abnormalities on a chest X-ray image (Photo courtesy of Lunit)
A new collaboration between Royal Philips (Amsterdam, The Netherlands) and Lunit (Seoul, South Korea) will make Lunit's AI software, the Insight CXR chest detection suite accessible to users of Philips' diagnostic X-ray solutions. CXR detects ten of the most common findings in a chest X-ray, incluindg small and subtle pulmonary nodules overlapped in the hilar shadow, ribs, heart, and diaphragm, enabling radiologists to reduce overlooked lung cancer cases, especially during regular check-ups.

Lunit Insight CXR is designed to instantly analyze of chest X-ray images by mapping radiological findings and displaying a scored calculation of actual existence. The algorithm shows a 97-99% accuracy rate in the detection of lung nodules, calcifications, consolidation, fibrosis, pneumothorax, pneumoperitoneum, cardiomegaly, pleural effusion, mediastinal widening, atelectasis, and tuberculosis. Data on the detected lesions is presented in the form of heatmaps and/or contour maps, with an abnormality score reflecting the AI’s calculation of the actual presence of the detected lesion.

“Radiology departments and their technologists are continually under pressure. They face high patient volumes, and every improvement in workflow can make a big impact,” said Daan van Manen, general manager for diagnostic X-ray at Philips. “Our partnership with Lunit to incorporate their diagnostic AI into our X-ray suite combines with a host of smart workflow features in the Philips radiography unified user interface (Eleva), across our digital radiography systems that enables a smooth and efficient, patient-focused workflow.”

“By partnering with Philips, one of the biggest medical device companies globally, our AI will be available to its significant global installed base. With the start of this partnership, we look forward to further expanding our collaboration to make data-driven medicine the new standard of care,” said Brandon Suh, CEO of Lunit. “Lunit will continue to build upon its current AI offering, making it better and better with time, and will continue to deliver best-in-class AI.”

Related Links:
Royal Philips
Lunit


Gold Member
Solid State Kv/Dose Multi-Sensor
AGMS-DM+
New
Ceiling-Mounted Digital Radiography System
Radiography 5000 C
New
Color Doppler Ultrasound System
KC20
Color Doppler Ultrasound System
DRE Crystal 4PX

Print article

Channels

Ultrasound

view channel
Image: CAM figures of testing images (Photo courtesy of SPJ; DOI:10.34133/research.0319)

Diagnostic System Automatically Analyzes TTE Images to Identify Congenital Heart Disease

Congenital heart disease (CHD) is one of the most prevalent congenital anomalies worldwide, presenting substantial health and financial challenges for affected patients. Early detection and treatment of... Read more

Nuclear Medicine

view channel
Image: Researchers have identified a new imaging biomarker for tumor responses to ICB therapy (Photo courtesy of 123RF)

New PET Biomarker Predicts Success of Immune Checkpoint Blockade Therapy

Immunotherapies, such as immune checkpoint blockade (ICB), have shown promising clinical results in treating melanoma, non-small cell lung cancer, and other tumor types. However, the effectiveness of these... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more