Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network
This addresses the problem of aligning retinal images from different modalities for ophthalmologists, with incremental improvements in accuracy.
The paper tackles multi-modal retinal image registration by proposing an end-to-end deep learning method that uses keypoint detection and graph neural networks, achieving higher registration accuracy than competing methods on synthetic and real datasets.
In ophthalmological imaging, multiple imaging systems, such as color fundus, infrared, fluorescein angiography, optical coherence tomography (OCT) or OCT angiography, are often involved to make a diagnosis of retinal disease. Multi-modal retinal registration techniques can assist ophthalmologists by providing a pixel-based comparison of aligned vessel structures in images from different modalities or acquisition times. To this end, we propose an end-to-end trainable deep learning method for multi-modal retinal image registration. Our method extracts convolutional features from the vessel structure for keypoint detection and description and uses a graph neural network for feature matching. The keypoint detection and description network and graph neural network are jointly trained in a self-supervised manner using synthetic multi-modal image pairs and are guided by synthetically sampled ground truth homographies. Our method demonstrates higher registration accuracy as competing methods for our synthetic retinal dataset and generalizes well for our real macula dataset and a public fundus dataset.