Modelling Geographic Atrophy Progression using Implicit Neural Representations

2026-08-11

AI Summary

This study addresses the challenge of highly individualized and unpredictable progression of geographic atrophy (GA) by introducing implicit neural representations (INRs) into longitudinal GA modeling. The authors propose an end-to-end method that encodes spatiotemporal coordinates to jointly learn a mapping function between a patient’s fundus autofluorescence (FAF) images and corresponding GA segmentations. This approach enables reconstruction of FAF images and associated GA regions at arbitrary time points, even under low-data conditions, thereby overcoming conventional models’ reliance on large datasets and limited generalizability. Experimental results demonstrate that the proposed method achieves the lowest mean absolute error in GA area prediction and the highest DICE score, while simultaneously producing high-quality image reconstructions.

Abstract

Age-related Macular Degeneration (AMD) is the major cause of blindness in the Western world. Its late dry phase is characterised by irreversible atrophic areas, namely Geographic Atrophy (GA). Longitudinal Fundus Autofluorescence (FAF) image acquisitions are currently the main tool for assessing lesion growth over time at the image level. However, due to its highly individualised progression, the evolution of late AMD remains poorly understood. In this work, we propose using Implicit Neural Representations (INRs) to model GA progression at the individual level in a low-data setting. Our approach generates both FAF and GA segmentation at both past and future time points. Among the comparison models, our method achieves competitive segmentation quality across different scenarios, yielding the lowest Mean Absolute Error (MAE) for the GA lesion area and the highest DICE score, without sacrificing FAF image quality. The code is available at https://github.com/SimoneSarrocco/ga-progression-with-inrs.

Problem

• Geographic Atrophy
• Age-related Macular Degeneration
• Longitudinal Modeling
• Low-data Setting
• Individualized Progression

Innovation

• Implicit Neural Representations
• Geographic Atrophy
• Longitudinal Modeling
• Low-data Learning
• Fundus Autofluorescence