Deep Features and Data Reduction for Classification of SD-OCT Images: Application to Diabetic Macular Edema

Diabetic Macular Edema (DME) is defined as the accumulation of extracellular fluids in the macular region of the eye, caused by Diabetic Retinopathy (DR) that will lead to irreversible vision loss if left untreated. This paper presents the use of a pre-trained Convolutional Neural Network (CNN) based model for the classification of Spectral Domain Optical Coherence Tomography (SD-OCT) images of Diabetic Macular Edema (DME) with feature reduction using Principal Component Analysis (PCA) and Bag of Words (BoW). The model is trained using SD-OCT dataset retrieved from the Singapore Eye Research Institute (SERI) and is evaluated using an 8-fold cross validation at the slide level and two patient leave out at the volume level. For the volume level, an accuracy of 96.88% is obtained for data that was preprocessed.