Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices

2025-08-27

AI Summary

This study addresses the challenge of dynamically monitoring neovascular activity in patients with exudative age-related macular degeneration (AMD). We propose a lesion progression classification and prediction method based on temporal pairs of optical coherence tomography (OCT) B-scans. Our core innovation is the Patch Progression Masked Autoencoder (PP-MAE), the first model capable of jointly generating future OCT scans from current ones and discriminating their pathological evolution patterns. Integrated within a dual-task collaborative learning framework that fuses convolutional neural networks (CNNs), PP-MAE models patch-level lesion progression across time points. Evaluated on the MARIO challenge, our method ranked among the top ten in both tasks—progression classification and progression prediction—demonstrating significant improvements in accuracy and generalizability for AMD progression forecasting. The approach provides an interpretable, data-driven paradigm to support personalized anti-VEGF treatment decisions.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Age-related Macular Degeneration (AMD) is a prevalent eye condition affecting visual acuity. Anti-vascular endothelial growth factor (anti-VEGF) treatments have been effective in slowing the progression of neovascular AMD, with better outcomes achieved through timely diagnosis and consistent monitoring. Tracking the progression of neovascular activity in OCT scans of patients with exudative AMD allows for the development of more personalized and effective treatment plans. This was the focus of the Monitoring Age-related Macular Degeneration Progression in Optical Coherence Tomography (MARIO) challenge, in which we participated. In Task 1, which involved classifying the evolution between two pairs of 2D slices from consecutive OCT acquisitions, we employed a fusion CNN network with model ensembling to further enhance the model's performance. For Task 2, which focused on predicting progression over the next three months based on current exam data, we proposed the Patch Progression Masked Autoencoder that generates an OCT for the next exam and then classifies the evolution between the current OCT and the one generated using our solution from Task 1. The results we achieved allowed us to place in the Top 10 for both tasks. Some team members are part of the same organization as the challenge organizers; therefore, we are not eligible to compete for the prize.

Problem

• Classifying evolution between consecutive 2D OCT slices
• Tracking neovascular AMD progression in OCT scans
• Predicting AMD progression over next three months

Innovation

• Fusion CNN network with model ensembling
• Patch Progression Masked Autoencoder for OCT generation
• Classifies evolution between current and generated OCTs