AI4CMR

AI4MedImaging

The AI4CMR software performs a automatic cardiac segmentation and interpretation of Cardiac Magnetic Resonance (CMR), allowing quantification of various parameters without the need for intervention by a medical professional.
It automatically identifies cases with normal left and right ventricle wall motion (regional contractility), aimed at increasing awareness for the cases with suspicious wall motion abnormalities to the reporting physicians.

Product specifications

Information source: Vendor
Last updated: July 26, 2022

General
Product name	AI4CMR
Company	AI4MedImaging
Subspeciality	Cardiac
Modality	MR
Disease targeted	Cardiac failure, Ischemic heart disease, Valvular heart disease, Cardiomyopathy, Cardiac function and morphology, Hypertensive cardiac disease, other pathologies that need assessment of cardiac function and morphology
Key-features	Heart ventricles segmentation, quantification of ventricular volumes, myocardial mass, and ejection fraction, wall motion classification
Suggested use	During: perception aid (prompting all abnormalities/results/heatmaps), interactive decision support (shows abnormalities/results only on demand), report suggestion
Data characteristics
Population	Patients examined by CMR imaging. Not recommended for children (age < 18yo).
Input	3D, 4D, Cine MRI, short-axis (mandatory), 2-chamber (optional), 3-chamber (optional), 4-chamber (optional), patient sex (mandatory), patient age (mandatory), patient height (optional), patient weight (optional), patient heart rate (optional)
Input format	DICOM
Output	Heart ventricles segmentation coordinates, report with values of ventricular volumes, myocardial mass, and ejection fraction, binary assessment of wall motion normality
Output format	JSON
Technology
Integration	Integration in standard reading environment (PACS), Integration RIS (Radiological Information System), Integration CIS (Clinical Information System), Integration via AI marketplace or distribution platform, Stand-alone third party application, Stand-alone webbased
Deployment	Locally virtualized (virtual machine, docker), Cloud-based, Hybrid solution
Trigger for analysis	Automatically, right after the image acquisition, On demand, triggered by a user through e.g. a button click, image upload, etc.
Processing time	10 - 60 seconds
Certification
CE	Certified, Class IIa , MDR
FDA	510(k) cleared, Class II
Market presence
On market since	09-2021
Distribution channels
Countries present (clinical, non-research use)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing
Pricing model	Pay-per-use, Subscription, One-off payment
Based on	Number of analyses
Evidence
Peer reviewed papers on performance
Non-peer reviewed papers on performance
Other relevant papers