Special Issue "Frontiers in Retinal Image Processing"

A special issue of Journal of Imaging (ISSN 2313-433X).

Deadline for manuscript submissions: 1 October 2021.

Special Issue Editors

Prof. Dr. Vasudevan Lakshminarayanan
E-Mail Website
Guest Editor
Theoretical and Experimental Epistemology Lab, School of Optometry and Vision Science, University of Waterloo, Waterloo, ON N2L3G1, Canada
Interests: optical physics and engineering; vision; noninvasive assessment of the visual system; mathematical methods; image processing
Special Issues and Collections in MDPI journals
Dr. P. Jidesh
E-Mail Website
Guest Editor
Department of Mathematical and Computational Sciences, National Institute of Technology Karnataka, Surathkal, 575 025 Karnataka, India
Interests: mathematical imaging; image processing; data compression; graph image processing

Special Issue Information

Dear Colleagues,

Visual impairment is a primary global challenge in the present era. Lack of awareness, shortage of resources and trained personnel, inability to seek immediate medical treatments, etc. can lead to several retinal disorders which can in turn lead to blindness or severe visual impairment. The human retina is examined through non-invasive procedures such as fundus photography, and optical coherence tomography. Other methods can include fluorescein angiography. From these images of the retina, ophthalmologists visually analyze and locate the retinal abnormalities of various retinal disorders. However, this is not feasible due to large numbers of patients, lack of adequately trained clinical personnel, as well as resources in the developing world, and underdeveloped or underserved areas in the developed world.

Automated retinal image analysis, which can be used in teleophthalmology, is thus of utmost importance to diagnose and grade, as well as monitor the progression or regression the disease after surgical and therapeutic intervention. State-of-the art devices such as portable OCT, smart-phone camera attachments, etc. have simplified the acquisition of retinal images to some extent. Nevertheless, the ever-increasing blind population and the availability of massive computational resources have spurred the urgent need to develop automated retinal imaging applications. The gamut of cutting-edge technologies such as Artificial Intelligence and Deep learning is a possible gateway to resolve these challenges. The domain of enhancement and registration of retinal images, multimodal analysis, and multiple disorder detection, as well as vendor-independent retinal image processing, are the limelight of retinal imaging.

Focusing on this direction, the Special Issue aims at research, broadly defined, that deals with multiple issues all orbiting around image acquisition and processing, which can be of assistance to the clinician and ophthalmic manufacturers. The objective of this issue is to gather in one venue relevant high-quality research and thereby contribute to the field of medical imaging and image processing in ophthalmology.

Topics of Interest:

The topics of interest include (but not limited to):

  • Automatic retinal disorders classification from retinal images
  • Early stage diagnosis and grading of retinal disorders
  • Hand-held or computerized devices for retinal image acquisition
  • Restoration and enhancement of retinal images
  • Analysis of retinal disorders using multi-modal retinal images
  • Segmentation of retinal images
  • Image registration
  • Computer vision based retinal image analysis
  • Volumetric analysis of retinal images using image processing techniques
  • Analysis of progressive retinal disorders using machine learning and deep learning
  • Cross-vendor supported applications to assist ophthalmologists
  • Multispectral retinal image analysis and applications

Prof. Dr. Vasudevan Lakshminarayanan
Dr. P. Jidesh
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.


  • retinal image processing
  • ophthalmology
  • classification
  • segmentation
  • registration
  • denoising
  • retinal disorders

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


EffUnet-SpaGen: An Efficient and Spatial Generative Approach to Glaucoma Detection
J. Imaging 2021, 7(6), 92; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7060092 - 30 May 2021
Viewed by 387
Current research in automated disease detection focuses on making algorithms “slimmer” reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In [...] Read more.
Current research in automated disease detection focuses on making algorithms “slimmer” reducing the need for large training datasets and accelerating recalibration for new data while achieving high accuracy. The development of slimmer models has become a hot research topic in medical imaging. In this work, we develop a two-phase model for glaucoma detection, identifying and exploiting a redundancy in fundus image data relating particularly to the geometry. We propose a novel algorithm for the cup and disc segmentation “EffUnet” with an efficient convolution block and combine this with an extended spatial generative approach for geometry modelling and classification, termed “SpaGen” We demonstrate the high accuracy achievable by EffUnet in detecting the optic disc and cup boundaries and show how our algorithm can be quickly trained with new data by recalibrating the EffUnet layer only. Our resulting glaucoma detection algorithm, “EffUnet-SpaGen”, is optimized to significantly reduce the computational burden while at the same time surpassing the current state-of-art in glaucoma detection algorithms with AUROC 0.997 and 0.969 in the benchmark online datasets ORIGA and DRISHTI, respectively. Our algorithm also allows deformed areas of the optic rim to be displayed and investigated, providing explainability, which is crucial to successful adoption and implementation in clinical settings. Full article
(This article belongs to the Special Issue Frontiers in Retinal Image Processing)
Show Figures

Figure 1

Back to TopTop