IDx-DR is an AI-based retinal diagnostic software designed to automatically detect more than mild diabetic retinopathy in adults with diabetes using retinal fundus images acquired with a specific fundus camera. It helps clinicians by providing screening results that indicate the presence or absence of disease, enabling timely referral and treatment to prevent vision loss.
Intended Use
IDx-DR is indicated for use by healthcare providers to automatically detect more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy.
Technology
IDx-DR consists of software components including IDx-DR Client (runs on customer computers connected to a fundus camera), IDx-Service (server-based analysis service), and IDx-DR Analysis software that processes retinal images to determine exam quality and detect diabetic retinopathy using an adaptive AI algorithm. It requires digital color fundus images with specified resolution from the Topcon TRC-NW400 fundus camera.
Performance
Clinical study with 900 diabetic patients showed IDx-DR achieved sensitivity of 87.4% and specificity of 89.5% for detecting more than mild diabetic retinopathy using fundus photography graded by a centralized reading center as reference standard. Repeatability and reproducibility testing showed 99.6% agreement of device outputs across multiple image sets and operators. Human factors testing confirmed usability by operators without prior retinal imaging experience.
Device Timeline
- 1
Submission
1/12/2018
2 months - 2
FDA Approval
4/11/2018
Ready to Sharpen Your Edge?
Join hundreds of your 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.