Abstract
Retinal template matching and registration is an important challenge in teleophthalmology with low-cost imaging devices. However, the images from such devices generally have a small field of view (FOV) and image quality degradations, making matching difficult. In this paper, we develop an efficient and accurate retinal matching technique that combines dimension reduction and mutual information (MI), called RetinaMatch. The dimension reduction initializes the MI optimization as a coarse localization process, which narrows the optimization domain and avoids local optima. The effectiveness of RetinaMatch is demonstrated on the open fundus image database STARE with simulated reduced FOV and anticipated degradations, and on retinal images acquired by adapter-based optics attached to a smartphone. RetinaMatch achieves a success rate over 94% on human retinal images with the matched target registration errors below 2 pixels on average, excluding the observer variability, outperforming standard template matching solutions. In the application of measuring vessel diameter repeatedly, single pixel errors are expected. In addition, our method can be used in the process of image mosaicking with area-based registration, providing a robust approach when feature-based methods fail. To the best of our knowledge, this is the first template matching algorithm for retina images with small template images from unconstrained retinal areas. In the context of the emerging mixed reality market, we envision automated retinal image matching and registration methods as transformative for advanced teleophthalmology and long-term retinal monitoring.
Highlights
T ELEMEDICINE applications are emerging at a rapid pace due to innovations in hardware and software, Manuscript received November 29, 2018; revised June 3, 2019; accepted June 7, 2019
We present a new template matching method, RetinaMatch, which can be used in remote retina health monitoring with affordable imaging devices
A principal component analysis (PCA)-based coarse localization method is proposed to provide a good initialization for the mutual information (MI)-based registration in the template matching
Summary
T ELEMEDICINE applications are emerging at a rapid pace due to innovations in hardware and software, Manuscript received November 29, 2018; revised June 3, 2019; accepted June 7, 2019. Erichson is with the Department of Applied Mathematics, University of Washington, Seattle, WA 98195 USA. Is with the Department of Ophthalmology, University of Washington, Seattle, WA 98195 USA. This paper has supplementary downloadable material available at http://ieeexplore.ieee.org., provided by the author. Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Low-cost teleophthalmology has been facilitated by smartphone-based fundus imaging. The emerging virtual and mixed reality sector may enable new teleophthalmology scenarios for long-term eye imaging and monitoring. In the case of portable fundus photography, non-mydriatic image quality is more vulnerable to distortions, such as uneven illumination, noise, blur and low contrast [1]. We address the challenging problem of automated retinal image matching and registration to enable future teleophthalmology applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
