Ceevra Reveal 3+
K233568Ceevra, Inc. · cleared 2023-12-05 · product code QIH · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“Ceevra Reveal 3+ (“Reveal 3+'), manufactured by Ceevra, Inc. (the "Company"), is a software as a medical device with two main functions: (1) it is used by Company personnel to generate three-dimensional (3D) images from existing patient CT and MR imaging, and (2) it is used by clinicians to view and interact with the 3D images during preoperative planning and intraoperatively.”
Algorithmmachine learning and other computer vision algorithms
source quote (p.3)
“Ceevra Reveal 3+ is intended as a medical imaging system that allows the processing, review, analysis, communication and media interchange of multi-dimensional digital images acquired from CT or MR imaging devices and that such processing may include the generation of preliminary segmentations of normal anatomy using software that employs machine learning and other computer vision algorithms.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.6)
“Additionally, the software validation activities were performed in accordance with IEC 62304:2006/Amd 1: 2015- Medical device software – Software life cycle processes, in addition to the FDA Guidance documents, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices” and “Content of Premarket Submission for Management of Cybersecurity in Medical Devices.””
Validation studies (2)
Retrospective clinical
n=141 cases
endpoints: Sørensen-Dice coefficient (DSC); Hausdorff distance metric at the 95th percentile (HD-95)
standards: IEC 62304:2006/Amd 1: 2015- Medical device software – Software life cycle processes, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, Content of Premarket Submission for Management of Cybersecurity in Medical Devices
Bench
sample size not stated
endpoints: Accuracy of measurement features (volumes of structures, diameters of structures, and distances between two points)
Reported performance (11 observations)
diceas written: “Sørensen-Dice coefficient (DSC) for prostate (MR prostate imaging)”0.87
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for bladder (MR prostate imaging)”0.9
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for kidney (CT abdomen imaging)”0.89
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for kidney (MR abdomen imaging)”0.87
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for artery (CT abdomen imaging)”0.87
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for artery (MR abdomen imaging)”0.83
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for vein (CT abdomen imaging)”0.86
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for vein (MR abdomen imaging)”0.81
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for artery (CT chest imaging)”0.85
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
diceas written: “Sørensen-Dice coefficient (DSC) for vein (CT chest imaging)”0.81
source quote (p.7)
“The performance of the machine learning models, characterized by the Sørensen-Dice coefficient (DSC) or the Hausdorff distance metric at the 95th percentile (HD-95), was as follows: prostate (from MR prostate imaging) 0.87 DSC; bladder (from MR prostate imaging) 0.90 DSC; neurovascular bundles (from MR prostate imaging) 7.8 mm HD-95; kidney (from CT abdomen imaging) 0.89 DSC; kidney (from MR abdomen imaging) 0.87 DSC; artery (from CT abdomen imaging) 0.87 DSC; artery (from MR abdomen imaging) 0.83 DSC; vein (from CT abdomen imaging) 0.86 DSC; vein (from MR abdomen imaging) 0.81 DSC; artery (from CT chest imaging) 0.85 DSC; vein (from CT chest imaging) 0.81 DSC.”
f1as written: “Accuracy of measurement features (volumes of structures, diameters of structures, and distances between two points)”stated without valueCI +/- 10%
source quote (p.7)
“All three types of measurements produced by Ceevra Reveal 3+ were verified to be accurate within a mean difference of +/- 10%.”
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
1
drift signals on this device
- re_clearance
The FDA AI/ML device list shows a newer 510(k) K243933 (decision 2025-03-04) from Ceevra, Inc. for a matching device line ("Ceevra Reveal 3+") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K243933
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).