Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction

ArXi:2604.16955v1 Announce Type: cross Quantitative prediction of future retinal appearance from longitudinal imaging would clinical decisions in progressive macular disease that currently rely on qualitative comparison or scalar progression scores. Recent methods have moved toward increasing generative complexity, but whether this complexity is necessary for slowly progressing retinal disease is unclear. We tested this through a controlled comparison of five conditioning configurations sharing one architecture and.