Two-stage color fundus image registration via Keypoint Refinement and Confidence-Guided Estimation.

Huiqi Li, Feihong Yan, Yubin Xu, Yiran Kong, Weihang Zhang

Journal: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society 2025;123():102554

PMID: 40294515

Full Text on Elsevier Science View on PubMed

Abstract

Color fundus images are widely used for diagnosing diseases such as Glaucoma, Cataracts, and Diabetic Retinopathy. The registration of color fundus images is crucial for assessing changes in fundus appearance to determine disease progression. In this paper, a novel two-stage framework is proposed for conducting end-to-end color fundus image registration without requiring any training or annotation. In the first stage, a pre-trained SuperPoint and SuperGlue network are used to obtain matching pairs, which are then refined based on their slopes. In the second stage, Confidence-Guided Transformation Matrix Estimation (CGTME) is proposed to estimate the final perspective transformation matrix. Specifically, a variant of 4-point algorithm, namely CG 4-point algorithm, is designed to adjust the contribution of matched points in estimating the perspective transformation matrix based on the confidence of SuperGlue. Then, we select the matched points with high confidence for the final estimation of transformation matrix. Experimental results show that our proposed algorithm can improve the registration performance effectively.

Address: Beijing Institute of Technology, No. 5, Zhong Guan Cun South Street, Beijing, 100081, China.; Beijing Institute of Technology, No. 5, Zhong Guan Cun South Street, Beijing, 100081, China. Electronic address: [email protected].

DOI: 10.1016/j.compmedimag.2025.102554

Link outs

Subscription / membership required

Full Text Sources:

MeSH Terms: Humans, Algorithms, Fundus Oculi, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted