Share Email Print
cover

Proceedings Paper

Automated detection of Schlemm's canal in spectral-domain optical coherence tomography
Author(s): Manu Tom; Vignesh Ramakrishnan; Christian van Oterendorp; Thomas M. Deserno
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Recent advances in optical coherence tomography (OCT) technology allow in vivo imaging of the complex network of intra-scleral aqueous veins in the anterior segment of the eye. Pathological changes in this network, draining the aqueous humor from the eye, are considered to play a role in intraocular pressure elevation, which can lead to glaucoma, one of the major causes of blindness in the world. Through acquisition of OCT volume scans of the anterior eye segment, we aim at reconstructing the three dimensional network of aqueous veins in healthy and glaucomatous subjects. A novel algorithm for segmentation of the three-dimensional (3D) vessel system in human Schlemms canal is presented analyzing frames of spectral domain OCT (SD-OCT) of the eyes surface in either horizontal or vertical orientation. Distortions such as vertical stripes are caused by the superficial blood vessels in the conjunctiva and the episclera. They are removed in the discrete Fourier domain (DFT) masking particular frequencies. Feature-based rigid registration of these noise-filtered images is then performed using the scale invariant feature transform (SIFT). Segmentation of the vessels deep in the sclera originating at or in the vicinity of or having indirect connection to the Schlemm's canal is then performed with 3D region growing technique. The segmented vessels are visualized in 3D providing diagnostically relevant information to the physicians. A proof-of-concept study was performed on a healthy volunteer before and after a pharmaceutical narrowing of Schlemm's canal. A relative decreases 17% was measured based on manual ground truth and the image processing method.

Paper Details

Date Published: 20 March 2015
PDF: 9 pages
Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis, 941430 (20 March 2015); doi: 10.1117/12.2082513
Show Author Affiliations
Manu Tom, RWTH Aachen Univ. (Germany)
Vignesh Ramakrishnan, RWTH Aachen Univ. (Germany)
Christian van Oterendorp, Georg-August-Univ. Hospital (Germany)
Thomas M. Deserno, RWTH Aachen Univ. (Germany)


Published in SPIE Proceedings Vol. 9414:
Medical Imaging 2015: Computer-Aided Diagnosis
Lubomir M. Hadjiiski; Georgia D. Tourassi, Editor(s)

© SPIE. Terms of Use
Back to Top