Automated detection of multiple structural changes of diabetic macular oedema in SDOCT retinal images through transfer learning in CNNs. Issue 16 (18th February 2021)

• Record Type: Journal Article
• Authors: Padmasini, Natarajan; Umamaheswari, Rengasamy
• Is Part Of: IET image processing. Volume 14:Issue 16(2020)
• Page Start: 4067
• Page End: 4075
• Publication Date: 2021-02-18
• Subjects: medical image processing -- biomedical optical imaging -- eye -- diseases -- optical tomography -- neural nets -- learning (artificial intelligence); automated detection -- multiple structural changes -- diabetic macular oedema -- SDOCT retinal images -- transfer learning -- diabetic maculopathy -- vision loss -- uncontrolled diabetes -- retinal layers -- macular detachment -- basically three structural changes -- DME viz -- CME -- SMD -- intra‐retinal fluid -- IRF -- spectral‐domain optical coherence tomography imaging modality -- automated algorithm -- deep learning -- ResNet‐50 performs -- classifying DME -- early‐stage DME -- structural deformities; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0612
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Diabetic Maculopathy, the major cause of vision loss, occurs due to uncontrolled diabetes. This affects the retinal layers of the eye causing bleeding of vessels, which results in Diabetic Macular Edema (DME), macular detachment etc., Basically three structural changes are involved in DME viz., Cystoid Macular Edema (CME), Serous Macular Detachment (SMD) and Intra Retinal Fluid (IRF). These changes may also coexist with each other such as CME with SMD or CME with IRF etc. In this work, the retinal images acquired through Spectral Domain Optical Coherence Tomography (SDOCT) imaging modality, which would provide high level of precision and resolution of the retinal layers are utilized. An automated algorithm to detect and differentiate seven types of DME based on deep learning is implemented using transfer learning on three Convolutional Neural Networks (CNNs), ResNet 50, VGGNet and AlexNet. In detection of DME, ResNet 50 performs excellently well, when compared with Alexnet and VGGNet, because of its depth and skip connection features. The average values of the statistical parameters such as accuracy (0.993), F1 score (0.975), Mathews Correlation Coefficient(MCC)(0.972) of ResNet are high when compared to that of AlexNet and VGGNet