Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections
| Affiliation auteurs | !!!! Error affiliation !!!! |
| Titre | Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections |
| Type de publication | Conference Paper |
| Year of Publication | 2016 |
| Auteurs | Alsaih K, Lemaitre G, Vall JMassich, Rastgoo M, Sidibe D, Wong TY, Lamoureux E, Milea D, Cheung CY, Meriaudeau F |
| Editor | Patton J, Barbieri R, Ji J, Jabbari E, Dokos S, Mukkamala R, Guiraud D, Jovanov E, Dhaher Y, Panescu D, Vangils M, Wheeler B, Dhawan AP |
| Conference Name | 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) |
| Publisher | IEEE Engn Med & Biol Soc |
| Conference Location | 345 E 47TH ST, NEW YORK, NY 10017 USA |
| Résumé | 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. |