Appropriate identification of age-related macular degeneration using OCT images

ABSTRACT

This paper presents an automatic approach for macular degeneration diagnostic by adding pertinent features in the evaluation process. In macular abnormality identification, the manual assessment of retina in OCT scan is an error prone task, especially in the preliminary behaviour levels. The efficiency of this presence is related to experience and the attention of ophthalmologists. Thereby, different techniques of retinal-image analysis help the option of obtaining a consistent, independent and overhead all rapid diagnosis to identify macular degeneration behaviour. We propose a computerised technique based on morphological parameters and a classification scheme to categorise subjects into two topics: normal and age related to macular degeneration (AMD). The obtained results prove that the use of a support vector machine (SVM) method is an efficient way to improve recognition for fast and accurate ophthalmology diagnostic.

KEYWORDS:

• Optical coherence tomography
• macular region segmentation
• watersheds
• support vector machines
• neural networks
• Convolutional Neural Networks (CNNs)

Acknowledgements

We are grateful for the support of Professor Laila Nacef from ophthalmology department at Hedi Raies Institute of Tunis, who provided us a part of data used in this work.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Marwa Hani

Marwa Hani is a PhD Student in Biophysics and medical imaging from the University of Tunis El Manar, ISTMT. She is a member of the research group in in Laboratory of Biophysics and medical technologies at the same university. Her research interests include deep learning methods, pattern recognition, Optical coherence tomography and Monte Carlo simulation.

Amine Ben Slama

Amine Ben Slama is a PhD Doctor in Biophysics and medical imaging from the University of Tunis El Manar, ISTMT. He is a member of research group in Laboratory of Biophysics and medical technologies at the same university. His research interests include signal processing and filtering, medical image segmentation and classification.

Imen Zghal

Imen Zghal is a professor of ophthalmology in Hedi Raies Institute of Tunis, Tunisia. Her research interests are focused on Optical coherence tomography, retinal imaging and retinal diseases exploration.

Hedi Trabelsi

Hedi Trabelsi born in 1975 in Tunis (Tunisia), he received the B.Sc. degree in Biophysics from the faculty of Sciences of Tunis, He is currently Professor at the higher institute of medical technologies of Tunisia University of Tunis El Manar, member of the Laboratory of biophysics and medical technologies. His research interests are focused on Diffuse optical tomography and physics simulation.