FractureDetect (FX)
K193417Imagen Technologies, Inc. · cleared 2020-07-30 · product code QBS · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“FractureDetect (FX) is a computer-assisted detection and diagnosis (CAD) software device to assist clinicians in detecting fractures during the review of radiographs of the musculoskeletal system.”
source quote (p.5)
“FX was developed using robust scientific principles and industry-standard deep learning algorithms for computer vision.”
source quote (p.7)
“HIPAA Compliant”
Validation studies (2)
Standalone
n=11,970 images
endpoints: detects fractures of the musculoskeletal system in radiographs with high sensitivity; high specificity; high Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC)
standards: FDA's Guidance for Industry and FDA Staff, “Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
Reader study (MRMC)
n=175 cases
endpoints: determine whether the diagnostic accuracy of readers aided by FX (“FX-Aided”) is superior to the diagnostic accuracy of readers unaided by FX (“FX-Unaided”) as determined by the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve
Reported performance (6 observations)
source quote (p.8)
“The results of standalone testing demonstrated that FX detects fractures of the musculoskeletal system in radiographs with high sensitivity (0.951; 95% Wilson's Confidence Interval (CI): 0.940, 0.960)”
source quote (p.8)
“high specificity (0.893; 95% Wilson's CI: 0.886, 0.898)”
source quote (p.8)
“and high Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) (0.982; 95% Bootstrap CI: 0.9790, 0.9850).”
source quote (p.11)
“Reader AUC was significantly improved from 0.912 to 0.952, a difference of 0.0406 (95% CI: 0.0127, 0.0685), across the 175 cases within FX's Indications for Use, spanning 12 study types (anatomic areas of interest) (p=.0043).”
source quote (p.11)
“Reader sensitivity improved from 0.819 (95% Wilson's CI: 0.794, 0.842) to 0.900 (95% Wilson's CI: 0.880, 0.917).”
source quote (p.11)
“Reader specificity improved from 0.890 (95% Wilson's CI: 0.879, 0.900) to 0.918 (95% Wilson's CI: 0.908, 0.927).”
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).