AI4CMR v2.0
K252084Ai4medimaging Medical Solutions S.A. · cleared 2026-02-11 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.6)
“AI4CMR v2.0 is a cloud-based solution designed to integrate to any third-party DICOM viewer application where the DICOM viewer serves as the user interface and the interface to a PACS or scanner for AI4CMR.”
source quote (p.10)
“Model Category: Convolutional Neural Network (U-Net architecture)”
source quote (p.10)
“The model is “locked,” meaning it does not adapt or change with new input data.”
Validation studies (2)
Standalone
n=167 cases · 1 site(s)
endpoints: Dice Similarity Coefficient (DSC)
standards: IEC 62304:2006+A1:2015
Bench
sample size not stated
endpoints: Total Forward Volume (TFV); Total Backward Volume (TBV); Maximum Velocity (Vmax)
standards: IEC 62304:2006+A1:2015
Reported performance (6 observations)
source quote (p.11)
“the model achieved DSC values of 0.952 for the ascending aorta”
source quote (p.11)
“0.957 for the descending aorta”
source quote (p.11)
“and 0.952 for the pulmonary artery”
source quote (p.11)
“Total Forward Volume (TFV): ICC 0.95”
source quote (p.11)
“Total Backward Volume (TBV): ICC 0.82”
source quote (p.11)
“Maximum Velocity (Vmax): ICC 0.95”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).