DeepContour (V1.0)
K232928Wisdom Technologies., Inc. · cleared 2024-05-07 · product code QKB · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“DeepContour is a deep learning based medical imaging software that allows trained healthcare professionals to use DeepContour as a tool to automatically process CT images.”
source quote (p.3)
“DeepContour is a deep learning based medical imaging software that allows trained healthcare professionals to use DeepContour as a tool to automatically process CT images.”
Validation studies (3)
Retrospective clinical
n=100 cases · 1 site(s)
endpoints: Dice coefficients
standards: RTOG clinical guidelines
Retrospective clinical
n=103 cases
endpoints: Dice coefficients
Bench
sample size not stated
endpoints: mean absolute error (MAE); root mean square error (RMSE); peak signal-to-noise ratio (PSNR); structural similarity (SSIM)
Reported performance (5 observations)
source quote (p.14)
“Brain 0.98±0.01(0.97)”
source quote (p.16)
“Heart 0.93±0.16(0.90”
source quote (p.15)
“Lung_L 0.98±0.05(0.96)”
source quote (p.17)
“SpinalCord 0.92±0.02(0.91)”
source quote (p.18)
“Spleen 0.90±0.05(0.88)”
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
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).