Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
This work addresses retinal image registration for medical applications, but it is incremental as it builds on existing learning-based feature detection methods.
The paper tackles the problem of aligning feature points across multi-modality retinal images by proposing a novel framework that integrates keypoint-based segmentation and self-supervised learning, achieving significant improvements in performance on public and in-house datasets.
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}.