A Straightforward Bifurcation Pattern-Based Fundus Image Registration Method

Abstract

Fundus image registration is crucial in eye disease examination, as it enables the alignment of overlapping fundus images, facilitating a comprehensive assessment of conditions like diabetic retinopathy, where a single image’s limited field of view might be insufficient. By combining multiple images, the field of view for retinal analysis is extended, and resolution is enhanced through super-resolution imaging. Moreover, this method facilitates patient follow-up through longitudinal studies. This paper proposes a straightforward method for fundus image registration based on bifurcations, which serve as prominent landmarks. The approach aims to establish a baseline for fundus image registration using these landmarks as feature points, addressing the current challenge of validation in this field. The proposed approach involves the use of a robust vascular tree segmentation method to detect feature points within a specified range. The method involves coarse vessel segmentation to analyze patterns in the skeleton of the segmentation foreground, followed by feature description based on the generation of a histogram of oriented gradients and determination of image relation through a transformation matrix. Image blending produces a seamless registered image. Evaluation on the FIRE dataset using registration error as the key parameter for accuracy demonstrates the method’s effectiveness. The results show the superior performance of the proposed method compared to other techniques using vessel-based feature extraction or partially based on SURF, achieving an area under the curve of 0.526 for the entire FIRE dataset.

Enhanced Vascular Bifurcations Mapping: Refining Fundus Image Registration

“…The key objective of this paper is to leverage bifurcations and crossovers along the morphological skeleton of blood vessel segmentation as feature points. The SBP-FIR method outlined in [9] demonstrated promising performance in registering pairs of fundus images. This proposal initially employs a pixel-wise segmentation method to define a region of interest over blood vessels, commonly used for detecting bifurcations and crossovers in fundus images [27][28][29][30][31].…”

“…The proposed method unfolds across four principal stages: feature extraction, feature matching, computation of the transformation matrix and subsequent image warping, concluding with image blending, as illustrated in Figure 1. Unlike the approach in [9], this method utilizes a deep learning-based technique for blood vessel seg-mentation. The primary objective is to enhance segmentation accuracy while concurrently reducing processing time, complemented by the utilization of the FREAK descriptor.…”

“…The proposed method demonstrates significant advancements compared to its predecessor [9], primarily attributed to a shift in the segmentation approach and feature extraction techniques. Transitioning from a pixel-wise segmentation to leveraging U-Net for blood vessel segmentation markedly heightens accuracy [38] and accelerates processing times.…”

“…Several techniques have been developed for registering fundus images, with some focusing on initial blood vessel detection. For example, the Straightforward Bifurcation Pattern-Based Fundus Image Registration method (SBP-FIR) described in [9] relies on pixelwise segmentation, while the approach in [10] utilizes the Frangi filter [11] for detecting tubular structures in fundus images. These methods employ thresholding-based segmentation and feature-based segmentation using filtering techniques, respectively.…”

“…This paper introduces an algorithm for registering pairs of fundus images. Unlike previous methodologies that relied on thresholding-based segmentation and the Frangi filter [9][10][11] for blood vessel delineation, this approach utilizes U-Net [12] to identify the specific region of interest within the image. The primary advantage of using U-Net over the Frangi filter lies in U-Net's autonomy in sensitivity parameter settings and its more efficient execution time for the entire segmentation process.…”