%K diabetic retinopathy; diagnostic imaging; factual database; human; image processing; macular edema; optical coherence tomography; procedures; sensitivity and specificity; support vector machine, Databases, Factual; Diabetic Retinopathy; Humans; Image Processing, Computer-Assisted; Macular Edema; Sensitivity and Specificity; Support Vector Machine; Tomography, Optical Coherence
%P 1344-1347
%O cited By 23; Conference of 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 ; Conference Date: 16 August 2016 Through 20 August 2016; Conference Code:124354
%I Institute of Electrical and Electronics Engineers Inc.
%X This paper deals with the automated detection of Diabetic Macular Edema (DME) on Optical Coherence Tomography (OCT) volumes. Our method considers a generic classification pipeline with preprocessing for noise removal and flattening of each B-Scan. Features such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are extracted and combined to create a set of different feature vectors which are fed to a linear-Support Vector Machines (SVM) Classifier. Experimental results show a promising sensitivity/specificity of 0.75/0.87 on a challenging dataset. © 2016 IEEE.
%L scholars6783
%D 2016
%V 2016-O
%A K. Alsaih
%A G. Lemaître
%A J.M. Vall
%A M. Rastgoo
%A D. Sidibé
%A T.Y. Wong
%A E. Lamoureux
%A D. Milea
%A C.Y. Cheung
%A F. Mériaudeau
%T Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: Application to DME detections
%J Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
%R 10.1109/EMBC.2016.7590956