Medihub Prostate

K233196

JLK Inc. · cleared 2024-06-21 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
MEDIHUB PROSTATE is an image processing software package for multi-parametric prostate MR image analysis.
Algorithmdeep learning model; AI-based algorithm
source quote (p.9)
MEDIHUB PROSTATE was developed by applying a deep learning technique on T2 prostate MRI.
Adaptive (vs locked)No
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.
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

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)

diceas written: “Dice coefficient (overall)0.928CI [0.925, 0.931]
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.
diceas written: “Dice Coefficient (White)0.929CI *[0.925, 0.933]
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
diceas written: “Dice Coefficient (African American)0.925CI *[0.902, 0.949]
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
diceas written: “Dice Coefficient (Asian)0.917CI *[nan, nan]
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
diceas written: “Dice Coefficient (< 60 age)0.938CI *[0.925, 0.950]
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
diceas written: “Dice Coefficient (>= 60 age)0.927CI *[0.923, 0.931]
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

0
recalls in product code, 24mo
3
MAUDE reports in code, 12mo
vs code's own 3-yr baseline
0
drift signals on this device

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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K233196