Chest X-ray

Rayscape CXR solution identifies a total of 148 findings on chest x-rays that are further on grouped into 17 main classes.The Rayscape’s algorithms show their location on the x-ray scan and provide doctors with additional information such as the CTR index and bone suppressed and subtracted versions of the medical image and a COVID 19 score.

*The company was previously named XVision, and the product CheXVision
Information source: Vendor
Last updated: Nov. 24, 2022

General Information

Product name Chest X-ray
Company Rayscape
Subspeciality Chest
Modality X-ray
Disease targeted 17 classes of pathologies: Lung Opacity, Atelectasis, Cardiomegly, Consolidation, Edema, Diaphragmatic Dysfunction, Emphysema, Fracture, Hilar/Mediastinal Disease, Interstitial Disease, Lung Lesion, Pleural Effusion, Pleural Other, Pneumothorax, Scoliosis, Support Devices, Tuberculosis
Key-features Detection of 148 chest findings grouped into 17 classes, bone suppression, bone subtraction, automated cardiothoracic ratio, COVID-19 score
Suggested use Before: flagging acute findings
During: perception aid (prompting all abnormalities/results/heatmaps)
After: diagnosis verification

Technical Specifications

Data characteristics
Population All chest x-rays of patients above 16 years old
Input Chest x-ray frontal PA or AP, lateral not supported
Input format DICOM
Output Bone subtracted XR, suppressed XR, probability score per abnormality, cardiothoracic ratio, COVID score
Output format DICOM
Integration Integration in standard reading environment (PACS), Integration via AI marketplace or distribution platform, Stand-alone webbased
Deployment Locally on dedicated hardware, Locally virtualized (virtual machine, docker), Cloud-based
Trigger for analysis Automatically, right after the image acquisition
Processing time 3 - 10 seconds


Certified, Class I , MDD
FDA No or not yet
Intended Use Statements
Intended use (according to CE)


Market presence
On market since 01-2021
Distribution channels Inffinit, Philips AI manager, deepcOS, Alma AI MARKETPLACE
Countries present (clinical, non-research use) 5 (Romania, Poland, Slovakia, Croatia, Hungary)
Paying clinical customers (institutes) 100
Research/test users (institutes) 8
Pricing model Subscription
Based on Number of analyses


Peer reviewed papers on performance
Non-peer reviewed papers on performance

  • Assisting Radiologists Through Automatic Cardiothoracic Ratio Calculation (read)

  • Assisting Radiologists in X-Ray Diagnostics (read)

Other relevant papers

  • Medical Whitepaper Rayscape (read)