ANDI 2.0
K252298Imeka Solutions, Inc. · cleared 2025-10-22 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.5)
“ANDI is software as a medical device (SaMD) that can be deployed on a cloud-based system, or installed on-premises.”
source quote (p.7)
“The device incorporates a pretrained third-party brain segmentation algorithm as detailed in the SBOM. The subject device employs an AI algorithm for grey matter segmentation to support volumetric quantification.”
source quote (p.7)
“The device incorporates a pretrained third-party brain segmentation algorithm as detailed in the SBOM.”
source quote (p.7)
“Guidance for Industry and FDA Staff – Guidance for Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions, September 2023”
Validation studies (1)
Retrospective clinical
n=71 patients
endpoints: accuracy of the AI-based brain extraction; accuracy and robustness of the brain regions segmentation; overall robustness of the processing pipeline; reproducibility of the brain regions segmentation
standards: ISO 14971:2019, Medical Devices – Application of Risk Management to Medical Devices, ANSI/AAMI/IEC 62304:2006/A1:2016, Medical Device Software - Software Life Cycle Processes, Digital Imaging and Communications in Medicine (DICOM) Set (NEMA PS 3.1 - 3.20), Guidance for Industry and FDA Staff – Guidance for the Content of Premarket Submissions for Device Software Functions, June 2023, Guidance for Industry and FDA Staff – Guidance for Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions, September 2023
Reported performance (2 observations)
source quote (p.8)
“Average Dice coefficients ranged from 0.89 to 0.96 for major subcortical brain structures”
source quote (p.8)
“and from 0.79 to 0.93 for major cortical brain structures”
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).