Journal article
Multimodal registration of SD-OCT volumes and fundus photographs using histograms of oriented gradients
Biomedical Optics Express, Vol.7(12), pp.5252-5267
2016
DOI: 10.1364/BOE.7.005252
PMCID: PMC5175567
PMID: 28018740
Abstract
With availability of different retinal imaging modalities such as fundus photography and spectral domain optical coherence tomography (SD-OCT), having a robust and accurate registration scheme to enable utilization of this complementary information is beneficial. The few existing fundus-OCT registration approaches contain a vessel segmentation step, as the retinal blood vessels are the most dominant structures that are in common between the pair of images. However, errors in the vessel segmentation from either modality may cause corresponding errors in the registration. In this paper, we propose a feature-based registration method for registering fundus photographs and SD-OCT projection images that benefits from vasculature structural information without requiring blood vessel segmentation. In particular, after a preprocessing step, a set of control points (CPs) are identified by looking for the corners in the images. Next, each CP is represented by a feature vector which encodes the local structural information via computing the histograms of oriented gradients (HOG) from the neighborhood of each CP. The best matching CPs are identified by calculating the distance of their corresponding feature vectors. After removing the incorrect matches the best affine transform that registers fundus photographs to SD-OCT projection images is computed using the random sample consensus (RANSAC) method. The proposed method was tested on 44 pairs of fundus and SD-OCT projection images of glaucoma patients and the result showed that the proposed method successfully registers the multimodal images and produced a registration error of 25.34 ± 12.34 μ m (0.84 ± 0.41 pixels).
Details
- Title: Subtitle
- Multimodal registration of SD-OCT volumes and fundus photographs using histograms of oriented gradients
- Creators
- Mohammad Saleh Miri - Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA 52242Michael D Abràmoff - Iowa City VA Health Care System, Iowa City, IA 52246Young H Kwon - Department of Ophthalmology and Visual Sciences, The University of Iowa, Iowa City, IA 52242Mona K Garvin - Iowa City VA Health Care System, Iowa City, IA 52246
- Resource Type
- Journal article
- Publication Details
- Biomedical Optics Express, Vol.7(12), pp.5252-5267
- Publisher
- Optical Society of America
- DOI
- 10.1364/BOE.7.005252
- PMID
- 28018740
- PMCID
- PMC5175567
- ISSN
- 2156-7085
- eISSN
- 2156-7085
- Grant note
- R01 EY018853; R01 EY023279 / National Institutes of Health (NIH) Marlene S. and Leonard A. Hadley Glaucoma Research Fund I01 RX001786; IK2RX000728 / U.S. Department of Veterans Affairs (VA)
- Language
- English
- Date published
- 2016
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Ophthalmology and Visual Sciences
- Record Identifier
- 9983805903902771
Metrics
16 Record Views