Abstract
Purpose: Retinal image registration is a useful tool for medical professionals. However, performance evaluation of registration methods has not been consistently assessed in the literature. To address that, a dataset comprised of retinal image pairs annotated with ground truth and an evaluation protocol for registration methods is proposed.Methods: The dataset is comprised by 134 retinal fundus image pairs. These pairs are classified into three categories, according to characteristics that are relevant to indicative registration applications. Such characteristics are the degree of overlap between images and the presence/absence of anatomical differences. Ground truth in the form of corresponding image points and a protocol to evaluate registration performance are provided.Results: The proposed protocol is shown to enable quantitative and comparative evaluation of retinal registration methods under a variety of conditions.Conclusion: This work enables the fair comparison of retinal registration methods. It also helps researchers to select the registration method that is most appropriate given a specific target use.
Highlights
Fundoscopy enables non-invasive observation of the microvascular circulation
Numerous publicly available datasets exist containing retinal images. They have been compiled for di erent purposes such as segmentation of diverse elements of the retina (CHASEDB, DRIONS-DB, Drishti-GS, DRIVE, HRF, MESSIDOR, ONHSD, and REVIEW, ), diagnosis (DIARETDB, ROC, DIARETDB, e-ophtha, STARE, INSPIRE-AVR, and VICAVR, ), user authentication (VARIA, ) and retinal image registration (FIRE and RODREP, )
Fundus Image Registration (FIRE) consists of three categories of retinal image pairs
Summary
Fundoscopy enables non-invasive observation of the microvascular circulation. Diagnosis and monitoring of diseases with commonly observed vasculopathy, such as diabetes and hypertension, can be assisted with the assessment of microcirculation by measuring and monitoring vascular morphology. Image registration – – a tool whose aim is to warp a test image to the coordinate frame of a reference image so that the same point is imaged at the same coordinates in both images – can be of great assistance for this task for several applications in retinal imaging. Such applications include super resolution, – mosaicing, – and longitudinal studies. The support of medical diagnosis requires accurate measurements This calls for methods, datasets, and protocols for quantifying the accuracy of retinal image analysis methods. No ground truth is provided for any other purpose besides retinal image registration
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Modeling and Artificial Intelligence in Ophthalmology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
