Dataset Information

Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection.

ABSTRACT: This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with DME versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool for DME, which is among the most common causes of irreversible vision loss in individuals with diabetes. Here, a classification framework with five distinctive steps is proposed and we present an extensive study of each step. Our method considers combination of various preprocessing steps in conjunction with Local Binary Patterns (LBP) features and different mapping strategies. Using linear and nonlinear classifiers, we tested the developed framework on a balanced cohort of 32 patients. Experimental results show that the proposed method outperforms the previous studies by achieving a Sensitivity (SE) and a Specificity (SP) of 81.2% and 93.7%, respectively. Our study concludes that the 3D features and high-level representation of 2D features using patches achieve the best results. However, the effects of preprocessing are inconsistent with different classifiers and feature configurations.

SUBMITTER: Lemaitre G

PROVIDER: S-EPMC4983398 | biostudies-other | 2016

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection.

Lemaître Guillaume G Rastgoo Mojdeh M Massich Joan J Cheung Carol Y CY Wong Tien Y TY Lamoureux Ecosse E Milea Dan D Mériaudeau Fabrice F Sidibé Désiré D

Journal of ophthalmology 20160731

This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with DME versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool for DME, which is among the most common causes of irreversible vision loss in individuals with diabetes. Here, a classification framework with five distinctive steps is proposed and we present an extensive study of each step. Our method considers combinatio ...[more]

PMID: 27555965

Similar Datasets

Project description:Neointimal infiltration with foamy macrophages is recognized as an early and important sign of de-novo atherosclerosis after stent implantation (neoatherosclerosis). Recent histopathological studies have proven that automated quantification of signal attenuation using intravascular optical coherence tomography (OCT) imaging allows for sensitive identification of macrophages in native atherosclerotic disease. Whether this is true for neointimal foam cells in the setting of neoatherosclerosis remains unknown. Autopsy samples of stented coronary arteries (n = 13 cases) were evaluated by histology and OCT. After co-registration with histology, the attenuation rate of emitted laser light was measured in regions with and without neointimal foamy macrophages relative to its peak intensity at the blood-tissue interface. Attenuation index was subsequently determined as slope of a regression curve fitted to individual data points. Receiver operating curve (ROC) analysis was used to establish an optimal cut-off for detecting foamy macrophages in homogenous and non-homogenous neointima, respectively. Finally, the tissue attenuation index was applied to confirm or exclude the presence of neointimal foamy macrophages in symptomatic patients presenting with in-stent restenosis and undergoing intravascular OCT imaging (n = 29 cases). Tissue attenuation index derived from post-mortem samples differed significantly between histologically confirmed regions with and without neointimal foamy macrophages (- 1.23 ± 1.42 vs. - 0.52 ± 1.79, p < 0.05). ROC analysis was able to distinguish neointima with foamy macrophage infiltration from neointima without (93% sensitivity, 73% specificity, cut-off - 0.79, AUC 0.87 for homogenous neointima and 40% sensitivity, 95% specificity, cut-off - 1.93, AUC 0.69 for non-homogenous neointima). In symptomatic patients presenting with in-stent restenosis after stent implantation and undergoing intravascular imaging with OCT, neointimal foamy macrophages were detected in 34.2% of homogenous and 43.6% of non-homogenous neointimal ROI's evaluated. OCT-derived and histopathologically validated tissue attenuation index enables identification of neointimal foamy macrophages in stented coronary arteries. Such image-based post-processing software algorithm may help discern and triage subjects at increased risk for device-related events.

Dataset Information

Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection.

Publications

Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure