Heuron ICH
K233247Heuron Co., Ltd. · cleared 2024-05-15 · product code QAS · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.3)
“Heuron ICH is radiological computer-aided triage and notification software designed for the analysis of non-contrast head CT images in adults or transitional adolescents aged 18 and older. This device is intended to aid appropriately trained medical specialists and hospital networks in streamlining workflow by identifying and communicating suspected positive findings of Intracranial hemorrhage (ICH).”
Algorithmartificial intelligence-based solution, deep learning (DL) technique of a convolutional neural network (CNN)
source quote (p.4)
“The Heuron ICH is an artificial intelligence-based solution that analyzes non-contrast CT images and provides a notification of suspected positive cases of intracranial hemorrhage (ICH) for prioritization of review. Heuron ICH uses deep learning (DL) technique of a convolutional neural network (CNN).”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.4)
“Heuron ICH registers with the hospital's Picture Archiving and Communication System (PACS) using IP, Port, AE title, and TLS authentication details. It automatically receives Non-Contrast Computed Tomography (NCCT) images in DICOM format from PACS. Upon connection request from PACS to Heuron ICH, the system verifies the IP, Port, AE title, and TLS authentication information before accepting the image transmission.”
Validation studies (1)
Retrospective clinical
n=600 images · 3 site(s)
endpoints: sensitivity; specificity; area under the receiver operating curve (AUC); time-to-notification
Reported performance (6 observations)
sensitivity86.3CI 81.9-90.3
source quote (p.7)
“Sensitivity of Heuron ICH was 86.3% (95% CI: 81.9-90.3)”
specificity87.6CI 83.9-91.0
source quote (p.7)
“specificity was 87.6% (95% CI: 83.9-91.0)”
aurocas written: “auc”0.945
source quote (p.8)
“The AUC was 0.945 when compared with the consensus diagnosis from radiologists.”
npvas written: “NPV”88.1
source quote (p.7)
“NPV was 88.1%”
ppvas written: “PPV”85.6
source quote (p.7)
“PPV was 85.6%.”
time_to_resultas written: “time-to-notification”60.3CI ±39.3 seconds (range 9-161 seconds)
source quote (p.8)
“The time-to-notification, 60.3 seconds±39.3 seconds (range 9-161 seconds), was similar to other cleared devices.”
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
0
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).