Color fundus image registration using a learning-based domain-specific landmark detection methodology

• Published in: Computers in biology and medicine 2022-01, Vol.140, p.105101-105101, Article 105101
• Main Authors: Rivas-Villar, David, Hervella, Álvaro S., Rouco, José, Novo, Jorge
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Bifurcations; Blood vessels; Clinical medicine; Color; Color fundus images; Color vision; Datasets; Deep learning; Diabetes mellitus; Diabetic retinopathy; Eye; Hypertension; Image processing; Image registration; Medical image registration; Medical imaging; Neural networks; Registration; Retina; Retinal images; Teaching methods
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.105101

Medical imaging, and particularly retinal imaging, allows to accurately diagnose many eye pathologies as well as some systemic diseases such as hypertension or diabetes. Registering these images is crucial to correctly compare key structures, not only within patients, but also to contrast data with a model or among a population. Currently, this field is dominated by complex classical methods because the novel deep learning methods cannot compete yet in terms of results and commonly used methods are difficult to adapt to the retinal domain. In this work, we propose a novel method to register color fundus images based on previous works which employed classical approaches to detect domain-specific landmarks. Instead, we propose to use deep learning methods for the detection of these highly-specific domain-related landmarks. Our method uses a neural network to detect the bifurcations and crossovers of the retinal blood vessels, whose arrangement and location are unique to each eye and person. This proposal is the first deep learning feature-based registration method in fundus imaging. These keypoints are matched using a method based on RANSAC (Random Sample Consensus) without the requirement to calculate complex descriptors. Our method was tested using the public FIRE dataset, although the landmark detection network was trained using the DRIVE dataset. Our method provides accurate results, a registration score of 0.657 for the whole FIRE dataset (0.908 for category S, 0.293 for category P and 0.660 for category A). Therefore, our proposal can compete with complex classical methods and beat the deep learning methods in the state of the art. •The proposed automatic method allows to accurately register retinal images.•A deep neural network detects highly specific domain-related landmarks.•The landmarks can be matched without descriptors using a RANSAC-based method.•Using deep learning landmarks instead of classical ones improves the registration.•The proposal outperforms state-of-the-art deep learning methods.