Retinal predictions using predicted future optical coherence tomography (OCT) images

The system generates synthetic predicted OCT imaging data using machine learning models to forecast retinal changes, addressing the challenge of predicting disease progression and treatment response in DME and nAMD, thereby enhancing disease management.

WO2026122958A1 Publication Date: 2026-06-11GENENTECH INC
3 Cites 0 Cited by

Patent Information

Application Number
PCT/US2025/058416
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-02
Filing Date
2025-12-05
Publication Date
2026-06-11

AI Technical Summary

Technical Problem

Existing methods struggle to accurately predict changes in retinal anatomical and functional features due to disease progression and treatment response in conditions like diabetic macular edema and neovascular age-related macular degeneration, which are leading causes of vision loss.

Method used

A system and method using machine learning models, particularly latent diffusion models and ControlNet neural networks, generate synthetic predicted optical coherence tomography (OCT) imaging data to forecast future retinal changes by processing characteristic data and baseline imaging, enabling personalized treatment regimens.

Benefits of technology

Enables accurate and reliable prediction of retinal features' responses to disease progression and treatment, facilitating effective management of retinal diseases like DME and nAMD.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A method and system for generating synthetic predicted OCT imaging data are provided. Input data including characteristic data and baseline imaging data associated with a subject at a baseline timepoint may be received. Input data associated with the subject for a set of future timepoints may be received. First and second machine learning models may be used to generate predicted OCT imaging data associated with the retina of the subject for the set of future timepoints, based on the input data.
Need to check novelty before this filing date? Find Prior Art