Retinal Nerve Fibre Layer Segmentation and Extraction of Retinal Features for Diagnosis of Glaucoma in Oct Images
M. Ponni Bala1, T. Keerthanashree2, K. Sheikdavood3
1Dr. M. Ponni Bala, Associate Professor, Department of Electronics and Instrumentation, Kongu Engineering College, Erode (Tamil Nadu), India.
2T. Keerthanashree, PG Student, Department of Electronics and Instrumentation, Kongu Engineering College, Erode (Tamil Nadu), India.
3K. Sheikdavood, Assistant Professor, Department of Electronics and Communication Engineering, M. Kumarasamy College of Engineering, Karur (Tamil Nadu), India.
Manuscript received on 28 April 2019 | Revised Manuscript received on 10 May 2019 | Manuscript Published on 17 May 2019 | PP: 574-579 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F11220476S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the medical field, wide varieties of applications can be dealt using image processing. Detection and screening of retinal diseases is one such application in image processing. Glaucoma is terrible form of a disease in which the subject’s optic nerve will be destroyed gradually which can lead to permanent loss of vision. Everyone is under risk from babies to senior citizens. The optic nerve is mainly composed of retinal fibers which are originated from the retinal ganglion cells. The optic nerve is considered like a bridge in between the retina and the brain. The retina is an area lying at the back of the eyeball. Optic nerve consists of delicate fibers which will be destroyed due to the excessive pressure due to glaucoma. Certain amount of fibers will be destroyed, which can lead to development of blind spots in the vision field. A patient’s sight at initial stage affects the peripheral vision or side vision and progresses towards the central vision at the advanced stage. The exact causes of optic nerve damage for glaucoma involve decreased blood flow of the optic nerve. In Glaucoma, due to the loss of tissues in the surrounding the nervous tissue in the central cup seems to be as an enlarged one. In addition to thinning of the Retinal Nerve Fiber Layer, structural changes in optic nerve rim is considered as very important screening tool for Glaucoma .In this research work, segmentation of Retinal Nerve Fiber Layer and extraction of retinal features from the retinal OCT image is proposed, in which by verifying the retinal images, time and energy of the ophthalmologists is reduced to an extent. The Nerve Fiber Layer is segmented by Semi-Automatic Region Growing Technique. The thickness of Retinal Nerve Fiber Layer (RNFL) are calculated for 60 images from the segmented nerve fiber layer image Then, the texture based feature extraction is done for 60 images and these features are used for classification purpose. The features such as RNFL Thickness, GLCM and LBP features are used to diagnose the Glaucoma. Different stages of Glaucoma can be effectively classified using Multi-Class Support Vector Machine.
Keywords: OCT, SVM, RNFL.
Scope of the Article: Image Processing and Pattern Recognition