Last Updated:
15th May 2023
Lunit INSIGHT CXR is an artificial intelligence (AI) solution that detects 10 different radiologic findings on chest X-rays as well as tuberculosis (TB) analysis feature. It is designed to provide a quick analysis in hard-to-reach areas regardless of internet connection, with proven versatility among different X-ray devices.
The AI solution generates (1) location markings for detected lesions in colour or outline, (2) abnormality scores reflecting the likelihood that the detected lesion is abnormal, and (3) an AI “case report” that summarizes the analysis result by each finding.
Certification
CE MDR Certification: MDR 731765 (first issued 2022 October 31st), Class IIa
Korea Ministry of Food and Drug Safety (MFDS) Approval: 20-24, Class 2
Brazil ANVISA: 80794390039
Development Stage
On the Market
Deployment
Online & Offline
Intended Age Group
14+ years
Target Setting
Primary health centres, general hospital (above primary level), teleradiology companies, government/public sector, examples national TB programmes, private sector
Current Market
Currently being used in over 80 countries
Input
Can analyze chest radiographs from multiple chest X-ray machines
Chest X-ray image format: DICOM
Chest X-ray type: posterior-anterior chest X-ray, anterior-posterior chest X-ray
Other requirements: product requires upload of an original image in the standard DICOM-format which contains appropriate DICOM metadata information in specific DICOM tags
Output
Structured report including:
Heat map
Score indicating potential presence as well as dichotomous output of each abnormality (radiologic findings)
Score indicating potential presence as well as dichotomous output of TB based on detected radiologic findings
Specification of the location of each abnormality (radiologic finding)
Default score threshold is set at 15 for all abnormalities including TB analysis.
Chest abnormalities detected by the product for which a separate abnormality score is given include: atelectasis, calcification, cardiomegaly, consolidation, fibrosis, mediastinal widening, nodule, pleural effusion, pneumoperitoneum, pneumothorax.
Hardware
Please contact insight@lunit.io for information.
Server
Please contact insight@lunit.io for information.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
Lunit INSIGHT CXR can be integrated with multiple CXR systems such as FujiFilm, GE, Samsung, Carestream, to name a few.
X ray file is transmitted from the X Ray system to Lunit AI by:
If the X-ray system has the function of sending & receiving of DICOM images via DICOM protocol, Lunit INSIGHT CXR can integrate with the system.
If the X-ray system has some limitation of receiving of DICOM images, the user can consider to integrate with Lunit INSIGHT CXR via PACS or HTTP API.
The X-ray system should generate DICOM images with the standard DICOM tags.
Lunit INSIGHT CXR can be integrated with a legacy picture archiving and communication system (PACS) which communicates via DICOM C-Store.
Software
Please contact insight@lunit.io for information.
Processing Time
About 5-20 seconds per X-ray
Data Sharing & Privacy
Server location: Amazon Web Services is used. Local or national servers can be set up if required
Data are not shared with the developer
There is an option to de-identify data. The Lunit DICOM Gateway anonymizes all personal information before transferring original images to the analysis server
Price
LUNIT INSIGHT offers volume-based pricing for the use of the license. When using the online solution, the volume-based price includes maintenance
When using the offline solution, maintenance is optional. Fees for infrastructure, customization and consulting are subject to change depending on the operating environment
Software Updates
Software is updated at least once a year
Please contact insight@lunit.io for pricing information
Product Development Method
Supervised deep learning (CNN - convoluted neural network)
Training
The product was trained on 1M chest X-rays.
Reference Standard
Biological reference standard: Sputum Xpert and/or culture test for TB
Publications
Over 20 scientific publications and references. A complete list of all publication related to Lunit INSIGHT CXR can be found on https://www.lunit.io/en/products/insight-cxr
This website works best with browsers other than Internet Explorer.