Skip to main content

Classification of SD-OCT volumes for DME detection: An anomaly detection approach

Publication ,  Conference
Sankar, S; Sidibé, D; Cheung, Y; Wong, TY; Lamoureux, E; Milea, D; Mériaudeau, F
Published in: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
January 1, 2016

Diabetic Macular Edema (DME) is the leading cause of blindness amongst diabetic patients worldwide. It is characterized by accumulation of water molecules in the macula leading to swelling. Early detection of the disease helps prevent further loss of vision. Naturally, automated detection of DME from Optical Coherence Tomography (OCT) volumes plays a key role. To this end, a pipeline for detecting DME diseases in OCT volumes is proposed in this paper. The method is based on anomaly detection using Gaussian Mixture Model (GMM). It starts with pre-processing the B-scans by resizing, flattening, filtering and extracting features from them. Both intensity and Local Binary Pattern (LBP) features are considered. The dimensionality of the extracted features is reduced using PCA. As the last stage, a GMM is fitted with features from normal volumes. During testing, features extracted from the test volume are evaluated with the fitted model for anomaly and classification is made based on the number of B-scans detected as outliers. The proposed method is tested on two OCT datasets achieving a sensitivity and a specificity of 80% and 93% on the first dataset, and 100% and 80% on the second one. Moreover, experiments show that the proposed method achieves better classification performances than other recently published works.

Duke Scholars

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510600201

Publication Date

January 1, 2016

Volume

9785
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Sankar, S., Sidibé, D., Cheung, Y., Wong, T. Y., Lamoureux, E., Milea, D., & Mériaudeau, F. (2016). Classification of SD-OCT volumes for DME detection: An anomaly detection approach. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9785). https://doi.org/10.1117/12.2216215
Sankar, S., D. Sidibé, Y. Cheung, T. Y. Wong, E. Lamoureux, D. Milea, and F. Mériaudeau. “Classification of SD-OCT volumes for DME detection: An anomaly detection approach.” In Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 9785, 2016. https://doi.org/10.1117/12.2216215.
Sankar S, Sidibé D, Cheung Y, Wong TY, Lamoureux E, Milea D, et al. Classification of SD-OCT volumes for DME detection: An anomaly detection approach. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2016.
Sankar, S., et al. “Classification of SD-OCT volumes for DME detection: An anomaly detection approach.” Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9785, 2016. Scopus, doi:10.1117/12.2216215.
Sankar S, Sidibé D, Cheung Y, Wong TY, Lamoureux E, Milea D, Mériaudeau F. Classification of SD-OCT volumes for DME detection: An anomaly detection approach. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2016.

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510600201

Publication Date

January 1, 2016

Volume

9785