EFAI RTSUITE CT HCAP-Segmentation System

K231928

Ever Fortune.AI Co., Ltd. · cleared 2023-09-25 · product code QKB · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“EFAI RTSuite CT HCAP-Segmentation System, herein referred to as EFAI HCAPSeg, is a standalone software that is designed to be used by trained radiation oncology professionals to automatically delineate organs-at-risk (OARs) on CT images.”
Algorithmdeep-learning algorithms
source quote (p.5)
“The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.11)
“Content of Premarket Submission for Management of Cybersecurity in Medical Devices.”

Validation studies (2)

Retrospective clinical

n=436 cases · 1 site(s)

endpoints: Overall, the mean Dice coefficient (DSC) was 0.85 for OAR contouring compared to the ground truth (GT).

standards: IEC 62304:2006/A1:2016 - Medical device software – Software life cycle processes, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices”(2005), Content of Premarket submissions for Devices Software Functions (11-04-2021), Content of Premarket Submission for Management of Cybersecurity in Medical Devices.

Retrospective clinical

n=157 cases

endpoints: For OARs present in both EFAI HCAPSeg and the comparison device, the mean Dice coefficient (DSC) of OARs for each body part (Head & Neck, Chest, and Abdomen & Pelvis) should be non-inferior to that of the comparison device, with a pre-specified margin.; For OARs unique to the EFAI HCAPSeg, the mean DSC of unique OARs should be superior to a pre-specified value.

standards: IEC 62304:2006/A1:2016 - Medical device software – Software life cycle processes, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices”(2005), Content of Premarket submissions for Devices Software Functions (11-04-2021), Content of Premarket Submission for Management of Cybersecurity in Medical Devices.

Reported performance (6 observations)

diceas written: “mean Dice coefficient (DSC) (Nonclinical Overall)”0.85
source quote (p.15)
“Overall, the mean Dice coefficient (DSC) was 0.85 for OAR contouring compared to the ground truth (GT).”
diceas written: “mean Dice coefficient (DSC) (Clinical Overall)”0.83
source quote (p.15)
“The overall performance showed a mean DSC of 0.83 and the non-inferiority tests indicated that EFAI HCAPSeg successfully met the primary endpoint across all body parts.”
diceas written: “Mean DSC (Head & Neck)”0.8
source quote (p.16)
“Head & Neck 0.80 0.21”
diceas written: “Mean DSC (Chest)”0.9
source quote (p.16)
“Chest 0.90 0.11”
diceas written: “Mean DSC (Abdomen & Pelvis)”0.9
source quote (p.16)
“Abdomen & Pelvis 0.90 0.14”
diceas written: “Mean DSC (Unique OAR)”0.82
source quote (p.16)
“Unique OAR 0.82 0.19”

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); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K231928