LARALAB
K242500LARALAB GmbH · cleared 2025-04-16 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.6)
“LARALAB is a stand-alone software developed to enable cardiologists, radiologists, heart surgeons and healthcare professionals (“Users”) to import, view and process Medical Images.”
source quote (p.6)
“In particular, the software generates pre-calculated automatic segmentations and measurements based on deterministic Deep Learning Algorithms.”
source quote (p.6)
“Similar, the subject device implements artificial intelligence including nonadaptive”
source quote (p.11)
“An external cybersecurity assessment, including penetration testing, was successfully completed to evaluate the system's security posture. No medium or high-risk vulnerabilities were identified, and a strong overall security posture with no critical issues was confirmed. The testing was conducted in accordance with the FDA guidance document Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions.”
Validation studies (1)
Retrospective clinical
n=60 patients
endpoints: The accuracy of automatic pre-calculated segmentations was evaluated using Dice score, Mean Surface Distance (MSD), and 95th percentile Hausdorff distance (95% HD) metrics.; The accuracy of automatic pre-calculated measurements was assessed using Bland-Altman analysis, which evaluated the mean bias and 95% limits of agreement between LARALAB's measurements and the ground-truth measurements.; The intraclass correlation coefficient (ICC) was also calculated to assess the consistency between the manual measurements (ground truth) generated with the predicate device by the clinical experts.
Reported performance (2 observations)
source quote (p.11)
“Segmentations: The Dice score analysis demonstrated that LARALAB achieved high accuracy in segmenting primary cardiovascular structures, with Dice scores ranging from 0.89 to 0.98 for major structures such as the LA, LV, RV, and RA.”
source quote (p.11)
“The ICC values were above 0.75 for all measurements, indicating excellent agreement between the clinical experts' manual measurements.”
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).