Share Email Print

Journal of Biomedical Optics • Open Access

Detection of meibomian glands and classification of meibography images
Author(s): Yang Wei Koh; Turgay Celik; Hwee Kuan Lee; Andrea Petznick; Louis H. Tong

Paper Abstract

Computational methods are presented that can automatically detect the length and width of meibomian glands imaged by infrared meibography without requiring any input from the user. The images are then automatically classified. The length of the glands are detected by first normalizing the pixel intensity, extracting stationary points, and then applying morphological operations. Gland widths are detected using scale invariant feature transform and analyzed using Shannon entropy. Features based on the gland lengths and widths are then used to train a linear classifier to accurately differentiate between healthy (specificity 96.1%) and unhealthy (sensitivity 97.9%) meibography images. The user-free computational method is fast, does not suffer from inter-observer variability, and can be useful in clinical studies where large number of images needs to be analyzed efficiently.

Paper Details

Date Published: 8 August 2012
PDF: 8 pages
J. Biomed. Opt. 17(8) 086008 doi: 10.1117/1.JBO.17.8.086008
Published in: Journal of Biomedical Optics Volume 17, Issue 8
Show Author Affiliations
Yang Wei Koh, Bioinformatics Institute (Singapore)
Turgay Celik, Bioinformatics Institute (Singapore)
Hwee Kuan Lee, Bioinformatics Institute (Singapore)
Andrea Petznick, Singapore Eye Research Institute (Singapore)
Louis H. Tong, Singapore National Eye Ctr. (Singapore)

© SPIE. Terms of Use
Back to Top