2010
DOI: 10.1117/1.3470116
|View full text |Cite
|
Sign up to set email alerts
|

Improving image segmentation performance and quantitative analysis via a computer-aided grading methodology for optical coherence tomography retinal image analysis

Abstract: Abstract. We demonstrate quantitative analysis and error correction of optical coherence tomography ͑OCT͒ retinal images by using a custom-built, computer-aided grading methodology. A total of 60 Stratus OCT ͑Carl Zeiss Meditec, Dublin, California͒ B-scans collected from ten normal healthy eyes are analyzed by two independent graders. The average retinal thickness per macular region is compared with the automated Stratus OCT results. Intergrader and intragrader reproducibility is calculated by Bland-Altman plo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

4
11
0

Year Published

2011
2011
2019
2019

Publication Types

Select...
7
1

Relationship

3
5

Authors

Journals

citations
Cited by 20 publications
(15 citation statements)
references
References 30 publications
4
11
0
Order By: Relevance
“…Sull et al compared TRT in ETDRS partitions obtained with several commercial devices and found the results obtained with SD-OCT to be similar 21. Our results of TRT were within the ranges, compared to the results reported by others 21,25. The thickness maps for six intraretinal layers obtained in the present study in EDTRS sections were also similar to those reported in a previous study,22 with some mild disparities.…”
Section: Discussionsupporting
confidence: 90%
See 1 more Smart Citation
“…Sull et al compared TRT in ETDRS partitions obtained with several commercial devices and found the results obtained with SD-OCT to be similar 21. Our results of TRT were within the ranges, compared to the results reported by others 21,25. The thickness maps for six intraretinal layers obtained in the present study in EDTRS sections were also similar to those reported in a previous study,22 with some mild disparities.…”
Section: Discussionsupporting
confidence: 90%
“…These findings may possibly be because the ONL in the present study included ONL and IS, and PR might include the outer segment of photoreceptors. The thickness values of OPL layer in ETDRS sectors were lower than those in other studies,22,25,37,39 but similar to the value reported by Liu et al35 Since the OCT used in the present study and by Liu et al are both custom-built systems with similar hardware configuration, similar results from healthy subjects may be expected. The remaining differences between the present study and other previous reports may also be simply due to the variation across normal subjects, imaging resolution, and algorithm differences.…”
Section: Discussionsupporting
confidence: 89%
“…The OCTRIMA software enables the segmentation of 6 layers of the retina on OCT images based on their optical densities: the RNFL, the GCL+IPL complex, the inner nuclear layer (INL), the outer plexiform layer (OPL), the outer nuclear layer (ONL) and retinal pigment epithelium (RPE). We have previously shown the high repeatability and reproducibility of OCTRIMA measurements in normal subjects with undisrupted retinal structure similarly to what is observed in patients with MS [20], [21]. The reproducibility was the highest for the thickness measurements of the ONL, GCC, GCL+IPL and RNFL, the inter- and intraexaminer, intervisit variabilities (<6 µm for all layers and all comparisons) being under the resolution of the Stratus OCT device for all layers [21].…”
Section: Methodssupporting
confidence: 69%
“…Manual correction of the boundary detection is enabled if segmentation errors are present. The repeatability and reproducibility of the thickness measurements was assessed earlier and was found to be very good [35], [36]. All the scans were segmented by the same blinded operator to reduce the possible bias caused by different operators and unblinded analysis.…”
Section: Methodsmentioning
confidence: 99%