20 July 2021
Lunit INSIGHT CXR is an artificial intelligence (AI) solution that detects 10 different radiologic findings on chest X-rays including tuberculosis (TB). 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 information for detected lesions in colour or outline, (2) abnormality scores reflecting the probability that the detected lesion is abnormal, and (3) an AI “case report” that summarizes the analysis result by each finding.
CE-marked Class I, Korea MFDS
On the market
Online & offline
Intended Age Group
Primary health centres, general hospital (above primary level), teleradiology companies, government/public sector, e.g. national TB programme, private sector
Currently being used in over 80 countries
»» Can be used to read images from any kind of chest X-ray machine (vendor neutral)
»» Chest X-ray image format: DICOM
»» Chest X-ray type: posterior-anterior chest X-ray, anterior-posterior chest X-ray, portable
»» Other requirements: product requires upload of an original image in the standard DICOM-format which contains appropriate DICOM metadata information in specific DICOM tags
Structured report including:
» Heat map
» Probability score as well as dichotomous output indicating whether each abnormality is present or absent
» Probability score as well as dichotomous output indicating whether TB is likely present or likely absent
» Specification of the location of each abnormality
Default threshold probability score is set at 15% for all abnormalities including TB.
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, and TB.
Lunit INSIGHT CXR can be generalized to any X-ray manufacturers computed radiography or digital radiography (CR/DR) and has been validated with over 20 leading X-ray manufacturers globally.
Lunit INSIGHT CXR can be integrated with a legacy picture archiving and communication system (PACS) which communicates via DICOM C-Store.
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
»» 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 is updated at least once a year
»» Please contact email@example.com for pricing information
Product Development Method
Supervised deep learning (CNN)
The product was trained on 1 M chest X-rays.
Chest computed tomography, pathology reports with chest abnormalities, and culture test result for TB
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
»» Hwang, E.J., Park, S., Jin, K.N. et al. Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. Clin Infect Dis. 2019;69(5):739-747. https://doi.org/10.1093/cid/ciy967
»» Hwang, E.J., Park, S., Jin, K.N. et al. Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs. JAMA Netw Open. 2019;2(3):e191095. https://doi.org/10.1001/jamanetworkopen.2019.1095
»» Lee, J.H., Park, S., Hwang, E.J. et al. Deep learning-based automated detection algorithm for active pulmonary tuberculosis on chest radiographs: diagnostic
»» Nam, J.G., Kim, M., Park, J. et al. Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs. Eur Respir J. 2021;57(5):2003061. https://doi.org/10.1183/13993003.03061-2020
»» Kim, E.Y., Kim, Y.J., Choi, W.J. et al. Performance of a deep-learning algorithm for referable thoracic abnormalities on chest radiographs: A multicenter study of a health screening cohort. PLoS One. 2021;16(2):e0246472. https://doi.org/10.1371/journal.pone.0246472
This website works best with browsers other than Internet Explorer.