DEEP LEARNING FOR IMAGE PROCESSING, APPLICATION TO DIABETIC MACULAR EDEMA (DME) DETECTION ON OPTICAL COHERENCE TOMOGRAPHY (OCT) IMAGES

Diabetic Macular Edema (DME) is a common eye disease which causes irreversible
vision loss for diabetic patients, if left untreated. Health care and associated costs for
treatment related to eye disease also increases with severity of case. Thus, early
diagnosis of DME could help in early treatment and prevent blindness. Using a
pretrained network of Convolutional Neural Network (CNN), this paper aims to create
a framework based on deep learning for DME recognition on Spectral Domain Optical
Coherence Tomography (SD-OCT) images through transfer learning, from a (limited)
dataset retrieved from Singapore Eye Research Institute (SERI). The dataset consists
of 16 volumes each for normal patients and DME patients with 128 images in each
volume.