Medihub Prostate
K233196JLK Inc. · cleared 2024-06-21 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.4)
“MEDIHUB PROSTATE is an image processing software package for multi-parametric prostate MR image analysis.”
source quote (p.9)
“MEDIHUB PROSTATE was developed by applying a deep learning technique on T2 prostate MRI.”
source quote (p.5)
“In semi-automatic mode, our device employs an AI-based algorithm to initially outline the prostate volume, and then it requires the user to edit, review and approve.”
Validation studies (3)
Retrospective clinical
n=114 images · 1 site(s)
endpoints: Dice coefficient; Hausdorff distance
Reader study (MRMC)
n=73 patients · 1 site(s)
endpoints: Dice coefficients
Bench
sample size not stated
endpoints: functionality; standalone performance of the prostate segmentation algorithm
standards: ISO 14971, IEC 62304, IEC 62366
Reported performance (6 observations)
source quote (p.9)
“The clinical testing results demonstrated that the overall Dice coefficient and Hausdorff distance were 0.928 and 2.171, respectively, with the 95% confidence intervals for these measurements being [0.925, 0.931] for the Dice coefficient and [1.097, 3.245] for the Hausdorff distance.”
source quote (p.10)
“95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by race”
source quote (p.10)
“95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by race”
source quote (p.10)
“95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by race”
source quote (p.10)
“95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by age”
source quote (p.10)
“95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by age”
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).