4D Graph-Based Segmentation for Reproducible and Sensitive Choroid Quantification From Longitudinal OCT Scans

View/ Open
Author
Oguz, Ipek
Abramoff, Michael D.
Zhang, Li
Lee, Kyungmoo
Zhang, Ellen Ziyi
Sonka, Milan
Note: Order does not necessarily reflect citation order of authors.
Published Version
https://doi.org/10.1167/iovs.15-18924Metadata
Show full item recordCitation
Oguz, Ipek, Michael D. Abramoff, Li Zhang, Kyungmoo Lee, Ellen Ziyi Zhang, and Milan Sonka. 2016. “4D Graph-Based Segmentation for Reproducible and Sensitive Choroid Quantification From Longitudinal OCT Scans.” Investigative Ophthalmology & Visual Science 57 (9): OCT621-OCT630. doi:10.1167/iovs.15-18924. http://dx.doi.org/10.1167/iovs.15-18924.Abstract
Purpose Longitudinal imaging is becoming more commonplace for studies of disease progression, response to treatment, and healthy maturation. Accurate and reproducible quantification methods are desirable to fully mine the wealth of data in such datasets. However, most current retinal OCT segmentation methods are cross-sectional and fail to leverage the inherent context present in longitudinal sequences of images. Methods: We propose a novel graph-based method for segmentation of multiple three-dimensional (3D) scans over time (termed 3D + time or 4D). The usefulness of this approach in retinal imaging is illustrated in the segmentation of the choroidal surfaces from longitudinal optical coherence tomography (OCT) scans. A total of 3219 synthetic (3070) and patient (149) OCT images were segmented for validation of our approach. Results: The results show that the proposed 4D segmentation method is significantly more reproducible (P < 0.001) than the 3D approach and is significantly more sensitive to temporal changes (P < 0.0001) achieved by the substantial increase of measurement robustness. Conclusions: This is the first automated 4D method for jointly quantifying choroidal thickness in longitudinal OCT studies. Our method is robust to image noise and produces more reproducible choroidal thickness measurements than a sequence of independent 3D segmentations, without sacrificing sensitivity to temporal changes.Other Sources
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5215413/pdf/Terms of Use
This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAACitable link to this page
http://nrs.harvard.edu/urn-3:HUL.InstRepos:30371062
Collections
- HMS Scholarly Articles [18129]
Contact administrator regarding this item (to report mistakes or request changes)