Opthalmology

One of the most active fields of work in the VARPA Group is the ophtalmology, in particular the analysis of eye fundus images (retinal images). The retinal image processing is a very interesting and demanding field, having a lot of practical applications, such as the development of applications for massive medical revision and the research in pharmacology effectiveness.

Collaborations

Complexo Hospitalario Universitario de A Coruña
Complexo Hospitalario Universitario de Santiago de Compostela
Hospital de Conxo
Hospital Naval de Ferrol

Institut d’Investigació Biomèdica de Girona Dr. Josep Trueta
Instituto Oftalmológico Gómez Ulla

Working fields

Drusen detection

Drusen are tiny white or yellow spots associated with the age-related macular degeneration (AMD). This disease can lead to severe loss central vision and adversely affect the patient’s quality of life. We have developed an automatic methodology to detect drusen in initial stages. This methodology is based a template matching technique to find the drusen in the interest areas. Currently, our work is focused on the analysis of the drusen evolution in OCTR sequences.

Red lesion detection

The diabetic retinopathy is a disease related to the diabetes that can cause blindness. One important symptom of diabetic retinopathy is the development of red lesions in the retina. We have developed an automatic methodology to analyse the retinal images in order to find this red lesions. This methodology is based on correlation filters and region growing segmentation techniques.

Arteriolar-to-Venular Ratio Computation

The retina Arteriolar-to-Venular ratio (AVR) is a parameter that helps the diagnosis of some pathologies, such as hypertension or arteriosclerosis. It is mainly computed as the ratio between the sum of artery calibers and the sum of vein calibers in several circumferences centered at the optic disc. We are currently developing and testing an automatic methodology to compute the AVR. This methodology involves the following steps:

  1. Optic disc location. It is the starting point. We are testing several algorithms to perform an efficient and reliable detection to the optic disc.
  2. Selection of Interest Radii centered at the optic disc.
  3. Vessel Detection and Caliber Measurement. We have developed a methodology based on snakes to measure the vessel diameter in concentric circumferences.
  4. Vessel Classification into Arteries and Veins. This is the most difficult step in the whole process due to the variability within inter-patient and intra-patient vessel contrast. We are testing several techniques and classifiers in order to minimize the misclassifications.
  5. AVR Computation. In the final step, we compute the AVR using the information obtained in the previous steps.

OCT-A

Angiography by Optical Coherence Tomography (OCT-A) is a non-invasive retinal imaging modality of recent appearance that allows the visualization of the vascular structure at predefined depths based on the detection of the blood movement through the retinal vasculature. In this way, OCT-A images allow us to measure the characteristics of the foveal vascular and avascular zones. Extracted parameters of this region can be used as prognostic factors that determine if the patient suffers from certain pathologies. The manual extraction of these biomedical parameters is a long, tedious and subjective process, introducing a significant intra and inter-expert variability, which penalizes the utility of the measurements. Our goals are the development of a fully automatic system that objectively segment and measure the region of the foveal avascular zone (FAZ) using this novel ophthalmological image modality, to ease the expert’s work, increasing their productivity and making viable the use of this type of vascular biomarkers.

Applications

Sirius

Our goals are the development of user-friendly applications for support diagnosis and disease monitoring. In this sense, we are working in the development of a complete application for the automatic computation of the Arteriolar-to-Venular ratio, the SIRIUS web application. The use of web technologies makes easier the software maintenance and the collaboration of several experts from different medical institutions.

Public databases

VICAVR database

The VICAVR database is a set of retinal images used for the computation of the A/V Ratio. The database currently includes 58 images. The images have been acquired with a TopCon non-mydriatic camera NW-100 model and are optic disc centered with a resolution of 768×584. The database includes the caliber of the vessels measured at different radii from the optic disc as well as the vessel type (artery/vein) labelled by three experts. If you are interested in using the VICAVR database, please send an email to: noelia.barreira@udc.es and you will receive an authentication password to access the database. This is intended for statistical purposes only, no private data or fee is required. If you use this image set for your work, please include a reference of VICAVR in it.

OCTAGON dataset

The OCTAGON dataset is a set of Angiography by Octical Coherence Tomography images (OCT-A) used to the segmentation of the Foveal Avascular Zone (FAZ). The dataset includes 144 healthy OCT-A images and 69 diabetic OCT-A images, divided into four groups, each one with 36 and about 17 OCT-A images, respectively. These groups are: 3×3 superficial, 3×3 deep, 6×6 superficial and 6×6 deep, where 3×3 and 6×6 are the zoom of the image and superficial/deep are the depth level of the extracted image. The healthy dataset includes OCT-A images from people classified in 6 age ranges: 10-19 years, 20-29 years, 30-39 years, 40-49 years, 50-59 years and 60-69 years. Each age range includes 3 different patients with information of left and right eyes for each one. Finally, for each eye, there are four different images: one 3×3 superficial image, one 3×3 deep image, one 6×6 superficial image and one 6×6 deep image. Each image have two manual labelled of expert clinicians of the FAZ and their quantification in the healthy OCT-A images, and one manual labelled in the diabetic OCT-A images. If you are interested in using the OCTAGON database, please send an email to: macarena.diaz1@udc.es and you will receive an authentication password to access the database. This is intended for statistical purposes only, no private data or fee is required. If you use this image set for your work, please include a reference of OCTAGON in it.

CLOUD dataset

The CLOUD dataset is a set of Optical Coherence Tomography of the Anterior Segment images (AS-OCT) used to the automatic identification and representation of the cornea-contact lens relationship. The dataset includes 112 AS-OCT images that were captured from 16 different patients. In particular, the images were obtained by an OCT Cirrus 500 scanner model of Carl Zeiss Meditec with an anterior segment module for users of scleral contact lens (SCL).

If you are interested in using the CLOUD database, please send an email to: joaquim.demoura@udc.es and you will receive an authentication password to access the database. This is intended for statistical purposes only, no private data or fee is required. If you use this image set for your work, please include a reference of CLOUD in it.

  • Cabaleiro, P.; de Moura, J.; Novo, J.; Charlón, P.; Ortega, M. «Automatic Identification and Representation of the Cornea–Contact Lens Relationship Using AS-OCT Images», Sensors, 19, 5087, 2019.

Main publications

  • M. Ortega, N. Barreira, J. Novo, M. G. Penedo, A. Pose-Reino, F. Gómez-Ulla, «SIRIUS: A Web-based system for retinal image analysis», International Journal of Medical Informatics, 79(10), 722-732, 2010.
Abstract
Purpose: Retinal image analysis can lead to early detection of several pathologies such as hypertension or diabetes. Screening processes require the evaluation of a high amount of visual data and, usually, collaboration between different experts and different health care centers. These usual routines demand new fast and automatic solutions to deal with these situations. This work introduces SIRIUS (System for the Integration of Retinal Images Understanding Services), a web-based system for image analysis in the retinal imaging field. Methods: SIRIUS provides a framework for ophthalmologists or other experts in the field to collaboratively work using retinal image-based applications in a distributed, fast and reliable environment. SIRIUS consists of three main components: The web client that users interact with, the web application server that processes all client petitions and the services module that performs the image processing and management tasks. The initial service implemented and discussed in this work is for the analysis of retinal microcirculation by means of semi-automatic computation of the Arteriolar-to-venular Ratio (AVR). Results: SIRIUS has been tested in a real environment of several health care systems to test its performance. In particular, the methodology for AVR computation was tested and validated by performing analysis from two different health care systems. The results showed that our AVR method outperforms previous approaches while providing a easily accessible environment for the analysis. Conclusions: SIRIUS is a web based application providing a fast and reliable environment for retinal experts to work with. The system allows the sharing of image and results between remote computers and provides automated methods to avoid differences inter-expert in the analysis of the images.
  • S. G. Vázquez, N. Barreira, M. G. Penedo, M. Ortega, A. Pose-Reino, «Improvements in Retinal Vessel Clustering Techniques:Towards the Automatic Computation of the Arterio Venous Ratio», Computing, Archives for Scientific Computing, 90 (3), 197-217, 2010.
Abstract
Retinal blood vessel structure is an important indicator for diagnosis of several diseases such as diabetes, hypertension, arteriosclerosis, or stroke. These pathologies cause early alterations in the blood vessels that affect veins and arteries differently. In this sense, the Arterio Venous Ratio is a measurement that evaluates these alterations and, consequently, the condition of the patient. Thus, a precise identification of both types of vessels is necessary in order to develop an automatic diagnosis system, to quantify the seriousness of disease, or to monitor the therapy. The classification of vessels into veins and arteries is difficult due to the inhomogeneity in the retinal image lightness and the similarity of both structures. In this paper, several image feature sets have been combined with three clustering strategies in order to find a suitable characterization methodology. The best strategy has managed to classify correctly the 86.34% of the vessels improving the results obtained with previous techniques.
  • S. G. Vázquez, N. Barreira, M. G. Penedo, M. Rodríguez-Blanco, «The significance of the vessel registration for a reliable computation of arteriovenous ratio», International Conference on Image Analysis and Recognition (ICIAR), Aveiro, Portugal, June 2012. (pending of publication).
Abstract
The arteriovenous ratio (AVR), this is, the relation between artery and vein widths, is a popular dimensionless measure to quantify changes in retinal microvasculature. However, its use in daily clinical practice has not been implanted due to the lack of reproducibility caused mainly by the laborious manual calculation and the dependence on the vessels selected for the estimation. This paper presents a vessel registration methodology in an AVR computation framework. The expert computes the AVR from a reference image in a semiautomatic manner and, after that, the AVR can be computed automatically from successive images of the same patient using the stored information from the reference image. The system has been evaluated in a large data set of 158 pairs of images and good correlation results between medical experts and system have been achieved.
  • M. Díaz, J. Novo, M. G. Penedo, M. Ortega, «Automatic extraction of vascularity measurements using OCT-A images», Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22st International Conference, KES-2018, 126, 273-281, Belgrado, Serbia, September 2018.
Abstract
Optical Coherence Tomography Angiography (OCT-A) is a new modality of ophthalmological imaging that stands out for being a non invasive capture technique that facilitates the analysis of the vascular characteristics of the eye fundus. In this paper, we propose a complete automatic methodology that identifies the vascular and avascular zones in OCT-A images, quantifying each one of them for their posterior use in clinical analyses and diagnostic processes. To achieve this, we firstly enhance the vascular characteristics to facilitate the posterior analysis. Then, a set of image processing techniques are combined to differentiate both vascular and avascular regions and, finally, measure their representative parameters. The proposed methodology was tested on a set of images that were marked by an expert ophthalmologist, being used as reference to perform the validation of the automatic proposed method. The proposed approach presented satisfactory results in the validation experiments with the vascular and avascular measurements, demonstrating their utility for the diagnostic and monitoring of vascular diseases that are frequently analysed through the retinal micro-circulation.
  • M. Díaz, J. Novo, P. Cutrín, F. Gómez-Ulla, M. G. Penedo, M. Ortega, «Automatic segmentation of the Foveal Avascular Zone in ophtalmological OCT-A images», PLoS One, 14(2), e0212364, 2019.
Abstract
Angiography by Optical Coherence Tomography (OCT-A) is a non-invasive retinal imaging modality of recent appearance that allows the visualization of the vascular structure at predefined depths based on the detection of the blood movement through the retinal vasculature. In this way, OCT-A images constitute a suitable scenario to analyse the retinal vascular properties of regions of interest as is the case of the macular area, measuring the characteristics