OsteoDetect
Imagen Technologies, Inc.OsteoDetect is an AI-driven software that helps clinicians detect distal radius fractures on adult wrist X-rays. It analyzes both posterior-anterior and lateral radiographs, highlighting potential fractures with bounding boxes to assist healthcare providers in diagnosing wrist injuries more accurately and quickly. The software serves as an adjunct, supporting clinical decision-making but not replacing the clinician's judgment.
Intended Use
OsteoDetect analyzes wrist radiographs using machine learning techniques to identify and highlight distal radius fractures during the review of posterior-anterior (PA) and lateral (LAT) radiographs of adult wrists.
Technology
OsteoDetect is a software-only device operating in three layers: Network, Presentation, and Decision layers. It accepts CR and DR DICOM images, filters eligible images, preprocesses them, applies a fracture detection deep learning model to analyze for distal radius fractures, then postprocesses results to generate a confidence score and bounding boxes for detected fractures. The output is an annotated DICOM image with fracture markings accessible in PACS.
Performance
The device underwent standalone software validation and a clinical reader study. Standalone testing on 1000 wrist X-rays demonstrated high diagnostic accuracy (AUC 0.965), sensitivity (92.1%), and specificity (90.2%) for distal radius fracture detection. The reader study with 24 clinicians showed OsteoDetect-aided reads had statistically significant improved diagnostic accuracy (AUC 0.889 vs 0.840 unaided, p=0.0056) and better sensitivity/specificity. Testing included localization accuracy and generalizability across patient subgroups and device types.
Ready to Sharpen Your Edge?
Subscribe to join 7,100+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.