Recent Automated Glaucoma Detection Techniques using Color Fundus Images
Prabhjot Kaur1, Praveen Kumar Khosla2
1Prabhjot Kaur, Assistant. Professor, Department of Electronics and Communications Engineering, G Pulla Reddy Engineering College Kurnool, Andhra Pradesh, India.
2Praveen Kumar Khosla, Assistant. Professor, Department of Electronics and Communications Engineering, G Pulla Reddy Engineering College Kurnool, Andhra Pradesh, India.
Manuscript received on 05 August 2019 | Revised Manuscript received on 12 August 2019 | Manuscript Published on 26 August 2019 | PP: 737-742 | Volume-8 Issue-9S August 2019 | Retrieval Number: I101190789S19/19©BEIESP | DOI: 10.35940/ijitee.I1119.0789S19
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: One of the areas in which C-DAC, Mohali is actively engaged, is development of AI powered fundus imaging system providing insight into several severe eye diseases. Glaucoma, one of the most hazardous ocular disease, continues to affect and burden a large section of our population. Neuropathy of optic nerve cells is the prime cause of glaucoma and is the second leading cause of blindness worldwide. It doesn’t manifest itself and is often termed as the silent thief of eye sight. The damage caused by glaucoma is irreversible. Therefore, it is imperative to detect glaucoma at an early stage. The medical literature related to glaucoma indicates that glaucoma detection is a complex process and depends on combination of several parameters. The conventional methods of hand-crafted feature extraction are tedious, time consuming and require human intervention. Even though many such systems have recently shown promising results, but these systems require extensive feature engineering and have limited representation power owing to varied morphology of the optic nerve head. Most of the proposed systems have targeted the parameter cup to disc ratio (CDR) for detection of glaucoma, but that may not be the best approach for building efficient, robust and accurate automated system for glaucoma diagnosis. This paper advocates the use of hybrid approach of manual feature crafting with deep learning. It holds promise of improving the accuracy of glaucoma diagnosis through the automated techniques. It is further proposed that if diagnosis based on CDR remains inconclusive other methods of diagnosis should be adopted to come to a certain conclusion.
Keywords: CDR, CNN, Deep Learning NN, Feature Extraction, Glaucoma, Fundus, ISNT rule, Transfer Learning.
Scope of the Article: Automated Software Design and Synthesis