Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images

Pratul P Srinivasan; Leo A Kim; Priyatham S Mettu; Scott W Cousins; Grant M Comer; Joseph A Izatt; Sina Farsiu

doi:10.1364/BOE.5.003568

Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images

Biomed Opt Express. 2014 Sep 12;5(10):3568-77. doi: 10.1364/BOE.5.003568. eCollection 2014 Oct 1.

Authors

Pratul P Srinivasan¹, Leo A Kim², Priyatham S Mettu³, Scott W Cousins³, Grant M Comer⁴, Joseph A Izatt⁵, Sina Farsiu⁶

Affiliations

¹ Department of Biomedical Engineering, Duke University, Durham 27708, USA ; Department of Computer Science, Duke University, Durham 27708, USA.
² Schepens Eye Research Institute, Massachusetts Eye and Ear Infirmary, Harvard University, Boston, 02114, USA.
³ Department of Ophthalmology, Duke University Medical Center, Durham 27710, USA.
⁴ Kellogg Eye Center, University of Michigan, Ann Arbor 48105, USA.
⁵ Department of Biomedical Engineering, Duke University, Durham 27708, USA ; Department of Ophthalmology, Duke University Medical Center, Durham 27710, USA.
⁶ Department of Biomedical Engineering, Duke University, Durham 27708, USA ; Department of Ophthalmology, Duke University Medical Center, Durham 27710, USA ; Department of Computer Science, Duke University, Durham 27708, USA ; Department of Electrical and Computer Engineering, Duke University, Durham 27708, USA.

Abstract

We present a novel fully automated algorithm for the detection of retinal diseases via optical coherence tomography (OCT) imaging. Our algorithm utilizes multiscale histograms of oriented gradient descriptors as feature vectors of a support vector machine based classifier. The spectral domain OCT data sets used for cross-validation consisted of volumetric scans acquired from 45 subjects: 15 normal subjects, 15 patients with dry age-related macular degeneration (AMD), and 15 patients with diabetic macular edema (DME). Our classifier correctly identified 100% of cases with AMD, 100% cases with DME, and 86.67% cases of normal subjects. This algorithm is a potentially impactful tool for the remote diagnosis of ophthalmic diseases.

Keywords: (100.0100) Image processing; (100.2960) Image analysis; (100.5010) Pattern recognition; (110.4500) Optical coherence tomography; (170.4470) Ophthalmology.

Abstract

Grants and funding