Posterior Choroidal Stroma Reduces Accuracy of Automated Segmentation of Outer Choroidal Boundary in Swept Source Optical Coherence Tomography

Chandrasekera, Erandi; Wong, Evan N; Sampson, Danuta M.; Alonso‐Caneiro, David; Chen, Fred K.

doi:10.1167/iovs.18-24665

Cited by 10 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several posterior boundaries of CT were proposed, and CT measurements can be substantially affected by the visibility of choroidscleral interface (CSI). [40][41][42][43][44] It was reported that automated outer choroidal boundary segmentation tends to identify the posterior limit of the choroidal vessel by SS-OCT. 40 Two investigators reviewed all the OCT scans, made correction when needed, and excluded images without clear choroid-scleral junction. However, the systematic errors could not be completely excluded due the wave length of the SS-OCT.…”

Section: Discussionmentioning

confidence: 99%

Choroidal Thickness in Diabetes and Diabetic Retinopathy: A Swept Source OCT Study

Wang

Liu

Qiu

et al. 2020

Invest. Ophthalmol. Vis. Sci.

View full text Add to dashboard Cite

Previous studies on the association between choroidal thickness (CT) and severity of diabetic retinopathy (DR) gave conflicting results. The aim of this study was to evaluate the CT changes in diabetic patients and associated factors in a large sample of Chinese patients with diabetes. METHODS. Type 2 diabetes mellitus patients without history of ocular treatment were recruited from the community health system in Guangzhou, China. The swept source OCT instrument was used to obtain high-definition retina and choroid images. The diabetic retinopathy (DR) status was graded based on the guidelines of the United Kingdom National Diabetic Eye Screening Programme. Univariate and multivariate linear regression analyses was used to explore the association of CT with DR severity, diabetic macular edema (DME), hemoglobin A1c, and vision function. RESULTS. A total of 1347 patients were included in the final analysis. After adjusting for other factors, the patients with stage R3 DR had significantly thinner CT (β =-29.1 μm, 95% CI-53.8 to-4.4, P = 0.021) in comparison in those with R0. After adjusting for other factors, the CTs were thicker than those in R0 patients with difference of 15.6 μm (95% CI 4.3-26.9, P = 0.007) for outer nasal sector, 15.7 μm (95% CI 3.8-25.5, P = 0.008) for outer inferior, and 12.2 μm (95% CI 0.4-24.0, P = 0.042) for inner inferior sector. The presence of DME and hemoglobin A1c levels did not significantly affect average CT. Higher average CT was significantly associated with better best corrected visual acuity, with a-0.02 LogMAR unit per 100 μm increase in average CT (95% CI-0.03 to-0.01, P < 0.001). CONCLUSIONS. CT increased in the early stage of DR, and further decreased with DR progression. DME was not significantly associated with CT. These findings provide more clues to suggest that choroid alterations play a role in the pathogenesis of DR.

show abstract

Section: Discussionmentioning

confidence: 99%

Choroidal Thickness in Diabetes and Diabetic Retinopathy: A Swept Source OCT Study

Wang

Liu

Qiu

et al. 2020

Invest. Ophthalmol. Vis. Sci.

View full text Add to dashboard Cite

show abstract

“…The findings presented here may be used to inform future work in the area of chorio-retinal boundary analysis in OCT images. Future studies should explore how these methods will perform in other OCT modalities, particularly swept-source OCT that has demonstrated a superior performance to visualize the deeper choroidal layer 85 compared to spectral domain OCT used in this study. It is worth noting that the images used in the current study are from young healthy participants, and therefore further work is required to examine these segmentation methods in cases of ocular pathology and in older populations.…”

Section: Discussionmentioning

confidence: 99%

Automatic choroidal segmentation in OCT images using supervised deep learning methods

Kugelman

Alonso‐Caneiro

Read

et al. 2019

Sci Rep

Self Cite

107

View full text Add to dashboard Cite

The analysis of the choroid in the eye is crucial for our understanding of a range of ocular diseases and physiological processes. Optical coherence tomography (OCT) imaging provides the ability to capture highly detailed cross-sectional images of the choroid yet only a very limited number of commercial OCT instruments provide methods for automatic segmentation of choroidal tissue. Manual annotation of the choroidal boundaries is often performed but this is impractical due to the lengthy time taken to analyse large volumes of images. Therefore, there is a pressing need for reliable and accurate methods to automatically segment choroidal tissue boundaries in OCT images. In this work, a variety of patch-based and fully-convolutional deep learning methods are proposed to accurately determine the location of the choroidal boundaries of interest. The effect of network architecture, patch-size and contrast enhancement methods was tested to better understand the optimal architecture and approach to maximize performance. The results are compared with manual boundary segmentation used as a ground-truth, as well as with a standard image analysis technique. Results of total retinal layer segmentation are also presented for comparison purposes. The findings presented here demonstrate the benefit of deep learning methods for segmentation of the chorio-retinal boundary analysis in OCT images.

show abstract

“…3D image analysis and choroidal 2D maps using SS-OCT images are potentially useful to explore the unknown pathogenesis of the choroid. To accomplish this purpose, the choroidal segmentation has several problems that cannot be easily overcome; low contrast of the C-S boundary, a deficit of the inner surface of the sclera, namely scleral canals for vessels or nerves, and the presence of a posterior stromal layer and lamina fusca 27 .…”

Section: Discussionmentioning

confidence: 99%

Semantic Segmentation of the Choroid in Swept Source Optical Coherence Tomography Images for Volumetrics

Tsuji

Sekiryu

Sugano

et al. 2020

Sci Rep

View full text Add to dashboard Cite

the choroid is a complex vascular tissue that is covered with the retinal pigment epithelium. Ultra high speed swept source optical coherence tomography (SS-oct) provides us with high-resolution cube scan images of the choroid. Robust segmentation techniques are required to reconstruct choroidal volume using SS-oct images. for automated segmentation, the delineation of the choroidal-scleral (c-S) boundary is key to accurate segmentation. Low contrast of the boundary, scleral canals formed by the vessel and the nerve, and the posterior stromal layer, may cause segmentation errors. Semantic segmentation is one of the applications of deep learning used to classify the parts of images related to the meanings of the subjects. We applied semantic segmentation to choroidal segmentation and measured the volume of the choroid. the measurement results were validated through comparison with those of other segmentation methods. As a result, semantic segmentation was able to segment the c-S boundary and choroidal volume adequately.

show abstract

Posterior Choroidal Stroma Reduces Accuracy of Automated Segmentation of Outer Choroidal Boundary in Swept Source Optical Coherence Tomography

Abstract: Automated outer choroidal boundary segmentation tends to identify the posterior limit of the choroidal vessel. Agreement between A-SFCT and M-SFCT is reduced by the presence of posterior stromal layer and lamina fusca. A-SFCT should be interpreted with RCJ and CSJ boundary grading.

Cited by 10 publications

References 24 publications

Choroidal Thickness in Diabetes and Diabetic Retinopathy: A Swept Source OCT Study

Choroidal Thickness in Diabetes and Diabetic Retinopathy: A Swept Source OCT Study

Automatic choroidal segmentation in OCT images using supervised deep learning methods

Semantic Segmentation of the Choroid in Swept Source Optical Coherence Tomography Images for Volumetrics

Contact Info

Product

Resources

About