Last Updated:
15th May 2023
VUNO Med-Chest X-ray is an artificial intelligence (AI)-based diagnostic supporting solution for chest X-ray. The solution accurately and instantly detects five of the most common thoracic findings such as nodule/mass, pneumothorax, interstitial opacity, pleural effusion, and consolidation and can therefore support doctors with the diagnosis of major lung diseases such as lung cancer, tuberculosis (TB) and pneumonia based on a combination of the findings.
Although pneumonia and tuberculosis detection functions have been developed, they are currently only available for demo or research purposes (approved for K-FDA). The pneumonia and tuberculosis diagnosis functions are expected to be CE-approved in 2024.
Certification
VUNO Med-Chest X-ray: MFDS (K-FDA) approved, CE certified, Ministry of Health of Malaysia, Saudi Food and Drug Authority(SFDA), FDA Thailand, Taiwan (TFDA)
Development Stage
On the Market
Deployment
On-device (Offline)
On-premise (Intranet)
Cloud (Online)
Intended Age Group
19+ years
Target Setting
Primary health centers, general hospital (above primary level), teleradiology companies, government/public sector, e.g. national TB programme, private sector
Current Market
Asia, Europe
Input
Chest X-ray image format: DICOM
Chest X-ray type: posterior-anterior chest X-ray, anterior-posterior chest X-ray
Output
Format: JPEG, PNG, DICOM, JSON
Result: Original image, Result image (Contour, Heatmap, Combined), Secondary Capture(SC) Report, Encapsulated PDF Report, Text Report
Specification of the location of each abnormality.
Chest abnormalities detected by the product for which a separate abnormality score is given include Nodule/Mass, Consolidation, Interstitial Opacity, Pleural effusion, and Pneumothorax.
Detects Tuberculosis (TB) and Pneumonia. (for research)
Lung findings included in tuberculosis: Nodule and Consolidation
Lung findings included in pneumonia: Consolidation and Interstitial Opacity.
Hardware
Requirements can vary depending on the business model. Please contact business@vuno.co for further information.
Server
VUNO Med-Chest X-ray leverages Amazon Web Services Cloud for the online product. A local or national server can be set up if required.
Hardware
Requirements can vary depending on the business model. Please contact business@vuno.co for further information.
Integration with X-ray Systems
Integration with PACS and Legacy Systems
VUNO Med-Chest X-Ray can be integrated with any DICOM-capable system, including but not limited to legacy picture archiving and communication systems and x-ray console systems. Furthermore, it provides a set of REST APIs that other solutions can use for integration. Some systems integrated with VUNO Med-Chest X-Ray include - INFINITT PACS, Samsung GM85, Taeyoung PACS, etc.
It is possible to integrate the product with the client’s legacy picture archiving and communication system (PACS) at no additional fee.
Software
Please contact business@vuno.co for further information.
Processing Time
It takes less than 5 seconds to analyse one DICOM image.
Data Sharing & Privacy
Server location (for online product)
VUNO Med-Chest X-ray leverages Amazon Web Services Cloud for online product. A local or national server can be set up if required.
Data are not shared with the developer.
There is an option to de-identify data. VUNO Med-Chest X-ray only receives patient ID and study date.
Software Updates
Can vary depending on the business model. Please contact business@vuno.co for further information. There is no price differentiation for private and public sector.
Product Development Method
Supervised deep learning (CNN, RNN)
Training
120 000 adult chest X-rays
Reference Standard
Computed tomography (CT), human reader
Publications
Sung, J., Park, S., Lee, S.M. et al. Added Value of Deep Learning-based Detection System for Multiple Major Findings on Chest Radiographs: A Randomized Crossover Study. Radiology. 2021;299(2):450-459. https://doi.org/10.1148/radiol.2021202818
Kim, YG., Cho, Y., Wu, CJ. et al. Short-term Reproducibility of Pulmonary Nodule and Mass Detection in Chest Radiographs: Comparison among Radiologists and Four Different Computer-Aided Detections with Convolutional Neural Net. Sci Rep. 2019;9:18738. https://doi.org/10.1038/s41598-019-55373-7
Park, S., Lee, S.M., Lee, K.H. et al. Deep learning-based detection system for multiclass lesions on chest radiographs: comparison with observer readings. Eur Radiol. 2020;30:1359–1368. https://doi.org/10.1007/s00330-019-06532-x
This website works best with browsers other than Internet Explorer.