Conference Proceedings
Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: Application to DME detections
K Alsaih, G Lemaître, JM Vall, M Rastgoo, D Sidibé, TY Wong, E Lamoureux, D Milea, CY Cheung, F Mériaudeau
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society EMBS | IEEE | Published : 2016
Abstract
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.
Grants
Funding Acknowledgements
The authors would like to acknowledge the financial support of the PHC Merlion from France and Singapore. The authors would like to acknowledge the Regional Burgundy Council which partially financially supported the current project under the PARI scheme 2.