AMD-Mamba: A Phenotype-Aware Multi-Modal Framework for Robust AMD Prognosis

Area of Science:

• Ophthalmology
• Artificial Intelligence
• Genetics

Background:

• Age-related macular degeneration (AMD) is a primary cause of irreversible vision loss.
• Accurate prognosis of AMD is essential for prompt clinical intervention.
• Existing prognostic models often lack comprehensive data integration and advanced feature extraction.

Purpose of the Study:

• To introduce AMD-Mamba, a novel multi-modal framework for AMD prognosis.
• To develop and validate a new AMD biomarker for improved disease progression prediction.
• To enhance the early detection of high-risk AMD patients.

Main Methods:

• Developed AMD-Mamba, a multi-modal framework integrating color fundus images, genetic variants, and socio-demographic data.
• Employed a novel metric learning strategy using AMD severity scale scores for richer feature representation.
• Utilized Vision Mamba for fused local and global information extraction, alongside multi-scale fusion of image and clinical data.

Main Results:

• The proposed AMD biomarker demonstrated significant predictive power for AMD progression.
• AMD-Mamba achieved improved detection of high-risk AMD patients in early stages when combined with existing variables.
• Experimental validation on the AREDS dataset (45,818 images, 52 genetic variants, 3 socio-demographic variables from 2,741 subjects) confirmed the framework's efficacy.

Conclusions:

• AMD-Mamba offers a promising multi-modal approach for precise AMD prognosis.
• The novel biomarker significantly contributes to identifying individuals at high risk for AMD progression.
• This framework facilitates proactive and personalized management strategies for age-related macular degeneration.