arXiv:2606.15129v1 Announce Type: cross Abstract: Color fundus photography (CFP) is the mainstay for large-scale retinal screening, yet its diagnostic capacity is constrained by the lack of depth-resolved structural information. Optical coherence tomography (OCT) provides cross-sectional retinal anatomy, but is less accessible in population-level screening. Here, we present EyeMVP, a cross-modal retinal foundation model that uses paired CFP--OCT pretraining to learn OCT-informed CFP representations. EyeMVP is pretrained on 674,893 strict same-eye same-day paired CFP--OCT image triples from 112
The proliferation of medical imaging data and advances in deep learning for cross-modal representation learning are enabling new diagnostic AI tools.
This development indicates a significant step towards more accessible and accurate early detection of retinal diseases using AI, potentially reducing diagnostic disparities.
AI models can now learn more comprehensive and robust representations of retinal health by integrating different imaging modalities, even when only one modality is widely available.
- · Ophthalmology AI companies
- · Healthcare providers in remote areas
- · Patients at risk of retinal diseases
- · Medical imaging hardware manufacturers
- · Traditional diagnostic methods reliant on single imaging modalities
Improved early detection rates for various retinal conditions will become more widespread.
The integration of AI into ophthalmology will accelerate, leading to new standard protocols for retinal screening.
Reduced healthcare costs associated with advanced-stage retinal disease treatments due to earlier intervention could be realized on a population scale.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI