New edge-cloud architecture streamlines diabetic retinopathy screening

Researchers have developed a two-tier edge-cloud architecture for automated diabetic retinopathy screening, aiming to improve efficiency in resource-constrained clinical settings. The system uses a lightweight model on the edge to triage images, sending only potentially referable cases to a more powerful cloud-based model for detailed grading. This approach reduces cloud processing by approximately 50% while maintaining high sensitivity for detecting referable diabetic retinopathy. AI

IMPACT This architecture could improve the efficiency and accessibility of AI-powered medical diagnostics in areas with limited connectivity.

RANK_REASON The cluster contains an academic paper detailing a new technical approach. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• APTOS 2019 Blindness Detection dataset
• diabetic retinopathy
• MobileNetV3-Small
• Nishi Doshi
• Non-referable DR
• Referable DR
• RETFound-DINOv2

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →