CDM Insights
K240680Oxford Brain Diagnostics Ltd · cleared 2024-12-06 · product code QIH · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“CDM Insights is a post-processing image analysis software that assists trained healthcare practitioners in viewing, analyzing, and evaluating MR brain images of adults > 45 years of age.”
AlgorithmAutomated segmentation and quantification of brain structures and lesions, automatic post-acquisition analysis of diffusion-weighted magnetic resonance imaging (DWI) data, and comparison of derived image metrics from multiple time-points.
source quote (p.5)
“CDM Insights is automated post-processing medical device software that is used by radiologists, neurologists, and other trained healthcare practitioners familiar with the post-processing of magnetic resonance images. It accepts DICOM images using supported protocols and performs: automatic segmentation and quantification of brain structures and lesions, automatic post-acquisition analysis of diffusion-weighted magnetic resonance imaging (DWI) data, and comparison of derived image metrics from multiple time-points.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.11)
“Cybersecurity documentation has been provided for CDM Insights in compliance with the FDA guidance document "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions." Medical device cybersecurity activities for CDM Insights were conducted to meet the requirements of multiple voluntary FDA Recognized Consensus Standards (i.e., AAMI TIR57 and ANSI AAMI SW96), as well as the FDA guidance documents "Cybersecurity for Networked Medical Devices Containing Off-the-Shelf (OTS) Software,” “Postmarket Management of Cybersecurity in Medical Devices" and "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions."”
Validation studies (5)
Bench
sample size not stated
standards: ISO 13485, ISO 14971, IEC 62304
Retrospective clinical
n=60 cases
endpoints: Accuracy of segmentation for brain regions and for white matter hyperintensities; Accuracy of cortical surfaces; Visual ratings of segmentation quality; Visual ratings of cortical surface quality
Retrospective clinical
n=121 patients
endpoints: Repeatability
Retrospective clinical
n=1,500 patients
endpoints: Reproducibility
Retrospective clinical
n=2,000 scans · 13 site(s)
endpoints: Accuracy of percentiles
Reported performance (9 observations)
diceas written: “White matter hyperintensities mean Dice overlap score”0.66CI 0.15
source quote (p.11)
“White matter hyperintensities were automatically segmented with mean (standard deviation, SD) Dice overlap score of 0.66 (0.15), that exceeded the acceptance criterion of 0.58 taken from the primary predicate.”
diceas written: “Orbito-frontal mean Dice score”0.58CI 0.10
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Superior-frontal mean Dice score”0.72CI 0.05
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Sensorimotor mean Dice score”0.69CI 0.14
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Ventral-temporal mean Dice score”0.58CI 0.05
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Anterior-cingulate mean Dice score”0.6CI 0.09
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Precuneus mean Dice score”0.58CI 0.08
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Lateral-occipital mean Dice score”0.59CI 0.11
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
diceas written: “Medial-occipital mean Dice score”0.63CI 0.06
source quote (p.11)
“For eight representative cortical regions, the mean (SD) Dice scores were as follows: Orbito-frontal 0.58 (0.10), Superior-frontal 0.72 (0.05), Sensorimotor 0.69 (0.14), Ventral-temporal 0.58 (0.05), Anterior-cingulate 0.60 (0.09), Precuneus 0.58 (0.08), Lateral-occipital 0.59 (0.11), Medial-occipital 0.63 (0.06).”
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).