Optimal Transport-based Graph Matching for 3D retinal OCT image registration

TL;DR

This paper introduces an efficient optimal transport-based graph matching framework for 3D mouse retinal OCT image registration, improving alignment accuracy in longitudinal studies of eye disease models.

Contribution

The novel OT-GM method combines adaptive vessel graph descriptors and 3D cube descriptors for precise 3D OCT image registration, outperforming existing methods.

Findings

Outperforms other registration methods on mouse OCT images.

Effective in aligning longitudinal OCT images with reasonable computation time.

Utilizes novel descriptors for robust vessel correspondence.

Abstract

Registration of longitudinal optical coherence tomography (OCT) images assists disease monitoring and is essential in image fusion applications. Mouse retinal OCT images are often collected for longitudinal study of eye disease models such as uveitis, but their quality is often poor compared with human imaging. This paper presents a novel but efficient framework involving an optimal transport based graph matching (OT-GM) method for 3D mouse OCT image registration. We first perform registration of fundus-like images obtained by projecting all b-scans of a volume on a plane orthogonal to them, hereafter referred to as the x-y plane. We introduce Adaptive Weighted Vessel Graph Descriptors (AWVGD) and 3D Cube Descriptors (CD) to identify the correspondence between nodes of graphs extracted from segmented vessels within the OCT projection images. The AWVGD comprises scaling, translation and rotation, which are computationally efficient, whereas CD exploits 3D spatial and frequency domain information. The OT-GM method subsequently performs the correct alignment in the x-y plane. Finally, registration along the direction orthogonal to the x-y plane (the z-direction) is guided by the segmentation of two important anatomical features peculiar to mouse b-scans, the Internal Limiting Membrane (ILM) and the hyaloid remnant (HR). Both subjective and objective evaluation results demonstrate that our framework outperforms other well-established methods on mouse OCT images within a reasonable execution time.