Clinical Decision Support System for Ophthalmologists for Eye Disease Classification

ABSTRACT

In medical applications, ocular OCT (optical coherence tomography) is used to assess glaucoma, macular degeneration, diabetic macular edema and other eye diseases as it is capable of showing the cross-sections of tissue layers. The creation of new blood vessels in the choroid layer of the eye is known as choroidal neovascularization (CNV). The aging and macular degeneration will represent the symptom DRUSEN. Our sharp central vision is affected due to DRUSEN. An irreversible vision loss is caused in diabetic patients due to diabetic macular edema (DME). It is mainly due to the leaking of blood vessels in the retina. This research work focus on designing a clinical decision support system to assist the ophthalmologist in classifying the three different types of eye diseases. The existing nine pre-trained CNN models are used for this purpose. The extracted features are used to generate the trained model that is further used for eye disease classification. The training accuracy, validation accuracy, training loss and validation loss are computed for 100 iterations for each pre-trained CNN models during training and validation. The trained model obtained after training is used as input to the classifier, which classifies the images under-diagnosis into NORMAL (normal eye), CNV, DME and DRUSEN. The performance metrics of the classifier designed using each pre-trained models are evaluated and compared for four classes independently. The test results show that the performance of the classifier implemented using the pre-trained model InceptionV3 is better than all other models.

KEYWORDS:

• Age-related macular degeneration (AMD)
• Choroidal neovascularization (CNV)
• Convolution neural networks (CNN)
• Deep learning (DL)
• Diabetic retinopathy (DR)
• Ophthalmologist
• Optical coherence tomography (OCT)
• Transfer learning (TL)

DISCLOSURE STATEMENT

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

Additional information

Notes on contributors

V. Sivamurugan

V Sivamurugan received his BTech and ME also in electronics engineering from Madras Institute of Technology Campus, Anna University, Chennai, India in 1991 and 2000, respectively. Currently, he is working as associate professor in the Department of Information Technology at Sri Sivasubramaniya Nadar College of Engineering, Chennai, India. His research interest includes low-power embedded system design, image captioning systems, deep learning and image analysis. He has four international journal papers and seven conference papers.

P. Indumathi

P Indumathi received a BE in communication systems from the College of Engineering, Anna University, Guindy India in 1993 and 1995 respectively. She completed her doctorate in traffic control in asynchronous transfer networks in 2007. She started her career in 1996 as a lecturer in the Electronics Engineering Department of the MIT campus of Anna University. Currently, she is working as professor in the Department of Electronics and Communication Engineering at MIT Campus, Anna University. She is passionate about communications and networking. Her paper won the best paper award from IETE in 1998. She has been actively involved in research in guiding doctorate students. Her research interest includes wireless communication, mobile computing, communication networks' design networks, performance analysis in LTE, embedded systems, Android-based system development and performance optimization and analysis in multicore embedded systems. She has 24 years of teaching experience. She has 22 international journal papers and 16 national journal papers to her credit. Email: [email protected]

V. Thanikachalam

V Thanikachalam has 21 years of teaching experience. His research interests include computer vision and image processing. He received his BE degree in computer science and engineering from Bharathidasan University Trichy, an ME and a PhD degree in computer science and engineering from Anna University Chennai, in 2006 and 2017, respectively. Currently, he is working as associate professor in the Department of Information Technology at Sri Sivasubramaniya Nadar College of Engineering. He has published various papers in reputed national and international conferences and journals in the field of image analysis, understanding and processing of images. Email: [email protected]

R. Rajakumar

R Rajakumar graduated from Sivanthi Aditanar College, Nagercoil, Tamilnadu, India and post-graduated from Kamaraj College, Tuticorin, Tamilnadu, India. He received his MPhil degree from Madurai Kamaraj University. He received his PhD degree from the Sathyabhama Institute of Science and Technology in 2013. Currently, he is working as professor in the Department of Mathematics, at Sathyabama Institute of Science and Technology. He has more than 20 years of experience in teaching. His research interests include the design of encryption algorithms and chaostic computing for image processing. He has 10 international journal papers and 7 national papers to his credit. Email: [email protected]