The CAD4COVID-CT software is based on deep learning technology to analyze Chest CT scans for abnormalities related to COVID-19. The software takes as input a Chest CT scan in dicom format. The input scan is checked for quality and the following outputs are produced: 1) The lobes are segmented and a lobe volume measurement is provided. 2) For each lobe, the affected area percentage is computed and summarized in a lobar severity score, ranging from [0-5]. 3) The overal CT severity score and affected area are computed from the 5 lobar analyses. All output is summarized in a output PDF report.
Product specifications Information source: Vendor
Last updated: Oct. 27, 2020
Product name CAD4COVID-CT
Company Thirona
Subspeciality Chest
Modality CT
Disease targeted COVID-19
Key-features COVID-19 analysis, volume quantifications, affected area quantifications, severity scores
Suggested use Before: stratifying reading process (non, single, double read), adapting worklist order, flagging acute findings
During: perception aid (prompting all abnormalities/results/heatmaps)
After: diagnosis verification
Data characteristics
Population All patients suspected of having COVID-19
Input 3D, Chest CT, multi-slice CT dicom, enhanced CT dicom
Input format slice-based dicom files or enhanced dicom file
Output segmentation overlay, severity score, affected area, table of quantified values, lobe volumes, emphysema score
Output format PDF report and JSON file
Integration Integration via AI marketplace or distribution platform, Stand-alone webbased
Deployment Locally virtualized (virtual machine, docker), Cloud-based
Trigger for analysis On demand, triggered by a user through e.g. a button click, image upload, etc.
Processing time 1 - 10 minutes
Certified, Class IIa , MDD
No or not yet
Market presence
On market since 06-2020
Distribution channels
Countries present (clinical, non-research use) 30+
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing model
Based on
Peer reviewed papers on performance
Non-peer reviewed papers on performance
Other relevant papers