Journal article
Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map
Medical Image Analysis, Vol.17(8), pp.907-928
12/2013
DOI: 10.1016/j.media.2013.05.006
PMCID: PMC3856938
PMID: 23837966
Abstract
•A novel method for segmentation of intraretinal layers of 3D SD-OCT scans.•The method is based on application of two sequential diffusion maps.•The method outperformed many other methods and is robust to blood vessel artifacts.•It can make a correct decision regarding the number of retinal layers.•It is robust across data from different manufacturers and the computation time is relatively low. Optical coherence tomography (OCT) is a powerful and noninvasive method for retinal imaging. In this paper, we introduce a fast segmentation method based on a new variant of spectral graph theory named diffusion maps. The research is performed on spectral domain (SD) OCT images depicting macular and optic nerve head appearance. The presented approach does not require edge-based image information in localizing most of boundaries and relies on regional image texture. Consequently, the proposed method demonstrates robustness in situations of low image contrast or poor layer-to-layer image gradients. Diffusion mapping applied to 2D and 3D OCT datasets is composed of two steps, one for partitioning the data into important and less important sections, and another one for localization of internal layers. In the first step, the pixels/voxels are grouped in rectangular/cubic sets to form a graph node. The weights of the graph are calculated based on geometric distances between pixels/voxels and differences of their mean intensity. The first diffusion map clusters the data into three parts, the second of which is the area of interest. The other two sections are eliminated from the remaining calculations. In the second step, the remaining area is subjected to another diffusion map assessment and the internal layers are localized based on their textural similarities. The proposed method was tested on 23 datasets from two patient groups (glaucoma and normals). The mean unsigned border positioning errors (mean±SD) was 8.52±3.13 and 7.56±2.95μm for the 2D and 3D methods, respectively.
Details
- Title: Subtitle
- Intra-retinal layer segmentation of 3D optical coherence tomography using coarse grained diffusion map
- Creators
- Raheleh Kafieh - Department of Physics and Biomedical Engineering, Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, IranHossein Rabbani - Department of Physics and Biomedical Engineering, Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, IranMichael D Abramoff - The Iowa Institute for Biomedical Imaging, The University of Iowa, IA 52242, USAMilan Sonka - The Iowa Institute for Biomedical Imaging, The University of Iowa, IA 52242, USA
- Resource Type
- Journal article
- Publication Details
- Medical Image Analysis, Vol.17(8), pp.907-928
- DOI
- 10.1016/j.media.2013.05.006
- PMID
- 23837966
- PMCID
- PMC3856938
- NLM abbreviation
- Med Image Anal
- ISSN
- 1361-8415
- eISSN
- 1361-8423
- Publisher
- Elsevier B.V
- Grant note
- DOI: 10.13039/100000002, name: National Institutes of Health, award: EY018853, EY019112, EB004640
- Language
- English
- Date published
- 12/2013
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9983806291202771
Metrics
37 Record Views