Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging

TL;DR

This paper introduces Retina IPA, a self-supervised learning framework that improves cross-modality retinal image registration by aligning keypoints through iterative learning and segmentation consistency, outperforming existing methods.

Contribution

The novel Retina IPA framework leverages self-supervised keypoint segmentation to enhance multimodal retinal image alignment, addressing challenges of unlabeled data and modality differences.

Findings

Significant performance improvements on public and in-house datasets.

Robust feature extraction across different retinal imaging modalities.

Open-source code and models available for research use.

Abstract

We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal images. Our model draws on the success of previous learning-based feature detection and description methods. To better leverage unlabeled data and constrain the model to reproduce relevant keypoints, we integrate a keypoint-based segmentation task. It is trained in a self-supervised manner by enforcing segmentation consistency between different augmentations of the same image. By incorporating a keypoint augmented self-supervised layer, we achieve robust feature extraction across modalities. Extensive evaluation on two public datasets and one in-house dataset demonstrates significant improvements in performance for modality-agnostic retinal feature alignment. Our code and model weights are publicly available at \url{https://github.com/MedICL-VU/RetinaIPA}.