top of page
Last Updated:
15th May 2023
DeepCheX® is an AI-assisted tool that helps clinicians and radiologists detect tuberculosis (TB) and various lung abnormalities on chest X-rays. After identifying and noting the lung abnormalities, DeepCheX® can produce a report of the findings to be reviewed by the radiologist. DeepCheX® aids hospitals by increasing staff efficiency, optimizing clinical workflows, and ultimately saving time and lives.
Certification
Pending
Development Stage
Under Development
Deployment
Online & Offline
Intended Age Group
18+ years
Target Setting
Primary health centres, general hospital (above primary level), teleradiology companies, government/public sector, e.g. national TB programme, private sector
Current Market
Taiwan
Input
DICOM, JPG and PNG;
Posterior-anterior CXR
Anterior-posterior CXR
Portable
Output
Heat Map
Dichotomous output indicating for each abnormality whether this is present or absent.
Dichotomous output only indicating whether TB is likely present or likely absent.
Probability score for TB
Probability score for each abnormality
Location of each abnormality
Heat map or bounding box indicating the location of the abnormality, list of abnormality and user-added diagnostics or annotations.
Other abnormalities: Atelectasis, Blunted costophrenic angle, Consolidation, Loculated pleural effusion, Mass, Nodule, Opacity, Pleural effusion, Pneumothorax
output taiwan.jpg
output taiwan.jpg
1/1
Hardware
Please contact Taimedimg@ailabs.tw for information.
Server
Please contact Taimedimg@ailabs.tw for information.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
DeepCheX® can be used to read images from any kind of chest X-ray machine (vendor neutral).
It is possible to directly integrate DeepCheX® with any chest X-ray machine through a network connection
It is possible to integrate DeepCheX with the client’s legacy PACS directly. This integration facilitates viewing of results and managing the screening workflow.
Data Sharing & Privacy
Data are not shared with the developer
All data are anonymized before analysis by DeepCheX
Software Updates
Software is updated at least once a year
Please contact Taimedimg@ailabs.tw for information.
Product Development Method
Supervised deep learning (Transformer base)
Training
Trained and tested on above 10,000 chest X-rays acquired globally.
Reference Standard
Human reader
Publications
This website works best with browsers other than Internet Explorer.
bottom of page