eprintid: 8610
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/86/10
datestamp: 2023-11-09 16:20:31
lastmod: 2023-11-09 16:20:31
status_changed: 2023-11-09 16:13:05
type: article
metadata_visibility: show
creators_name: Alsaih, K.
creators_name: Lemaitre, G.
creators_name: Rastgoo, M.
creators_name: Massich, J.
creators_name: Sidibé, D.
creators_name: Meriaudeau, F.
title: Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images
ispublished: pub
keywords: Classification (of information); Coherent light; Image classification; Learning systems; Ophthalmology; Principal component analysis; Support vector machines, Automatic classification; Feature representation; Histogram of oriented gradients; Linear Support Vector Machines; Machine learning techniques; Multi-resolution approach; SD-OCT; Spectral domain optical coherence tomographies, Optical tomography, Article; B scan; classifier; diabetic macular edema; disease classification; histogram; human; image quality; machine learning; optical coherence tomography device; principal component analysis; priority journal; retina exudate; retinal thickness; sample size; sensitivity and specificity; spectral domain optical coherence tomography; subretinal fluid; support vector machine; diabetic retinopathy; diagnostic imaging; image processing; macular edema; optical coherence tomography; procedures; signal noise ratio, Diabetic Retinopathy; Humans; Image Processing, Computer-Assisted; Machine Learning; Macular Edema; Signal-To-Noise Ratio; Tomography, Optical Coherence
note: cited By 92
abstract: Background: Spectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology of the retina as well as the retina layers. Methods: The dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px � 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations. Results and conclusion: Besides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP 16-ri vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5, respectively. © 2017 The Author(s).
date: 2017
publisher: BioMed Central Ltd.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85020164886&doi=10.1186%2fs12938-017-0352-9&partnerID=40&md5=fe28b687341ec96a6ac5fc13d896459b
id_number: 10.1186/s12938-017-0352-9
full_text_status: none
publication: BioMedical Engineering Online
volume: 16
number: 1
refereed: TRUE
issn: 1475925X
citation:   Alsaih, K. and Lemaitre, G. and Rastgoo, M. and Massich, J. and Sidibé, D. and Meriaudeau, F.  (2017) Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images.  BioMedical Engineering Online, 16 (1).   ISSN 1475925X