AI fuses OCT and OCTA images for improved diabetic retinopathy diagnosis

Researchers have developed a novel cross-modal fusion technique combining Optical Coherence Tomography (OCT) and OCT angiography (OCTA) en face images to improve the diagnosis of diabetic retinopathy. This method utilizes a bidirectional cross-modal attention network to integrate structural OCT data with vascular OCTA information. Experiments on two datasets demonstrated that the fused approach significantly outperforms models relying on OCT data alone, with translated OCTA (TR OCTA) showing comparable or superior results to ground-truth OCTA and enhancing robustness to domain shifts. AI

IMPACT This fusion technique could lead to more accurate and accessible screening tools for diabetic retinopathy, especially in resource-limited settings.

RANK_REASON The item is an academic paper detailing a new method for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• bidirectional cross-modal attention network
• ConvNeXt V2
• diabetic retinopathy
• Optical Coherence Tomography
• Rashadul Hasan Badhon
• University of Illinois Chicago

• paper
• product

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