Retinal thickness estimation from SD-OCT macular scans

N. Hammes, L. Racette, B. C. Samuels, G. Tsechpenakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Glaucoma, a leading cause of blindness worldwide, can be detected using retinal thicknesses from spectral-domain optical coherence tomography (SD-OCT) scans of the macula. We calculate the desired thickness maps as the distance between the inner-limiting membrane (ILM) and retinal pigmented epithelium (RPE) of the retina. To delineate these two layers, we use a set of two deformable open surfaces that are driven by intensity contrast, while preserving their shape and topology properties, i.e. local surface smoothness and inter-surface distance smoothness. To evaluate our method, qualified graders manually segmented 30 random sections from 20 OCT image stacks, in triplicate; we make comparisons with obtained ground-truth and the clinically tested Heidelberg Spectralis segmentation. We show the superiority of our method with respect to accuracy and average execution time (∼7 secs), validating it as a clinical tool.

Original languageEnglish (US)
Title of host publicationProceedings - International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages213-217
Number of pages5
Volume2015-July
ISBN (Print)9781479923748
DOIs
StatePublished - Jul 21 2015
Event12th IEEE International Symposium on Biomedical Imaging, ISBI 2015 - Brooklyn, United States
Duration: Apr 16 2015Apr 19 2015

Other

Other12th IEEE International Symposium on Biomedical Imaging, ISBI 2015
CountryUnited States
CityBrooklyn
Period4/16/154/19/15

Fingerprint

Optical tomography
Optical Coherence Tomography
Blindness
Glaucoma
Retina
Epithelium
Membranes
Topology

Keywords

  • early detection of glaucoma
  • interacting deformable surfaces
  • Retinal thickness

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Hammes, N., Racette, L., Samuels, B. C., & Tsechpenakis, G. (2015). Retinal thickness estimation from SD-OCT macular scans. In Proceedings - International Symposium on Biomedical Imaging (Vol. 2015-July, pp. 213-217). [7163852] IEEE Computer Society. https://doi.org/10.1109/ISBI.2015.7163852

Retinal thickness estimation from SD-OCT macular scans. / Hammes, N.; Racette, L.; Samuels, B. C.; Tsechpenakis, G.

Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. p. 213-217 7163852.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hammes, N, Racette, L, Samuels, BC & Tsechpenakis, G 2015, Retinal thickness estimation from SD-OCT macular scans. in Proceedings - International Symposium on Biomedical Imaging. vol. 2015-July, 7163852, IEEE Computer Society, pp. 213-217, 12th IEEE International Symposium on Biomedical Imaging, ISBI 2015, Brooklyn, United States, 4/16/15. https://doi.org/10.1109/ISBI.2015.7163852
Hammes N, Racette L, Samuels BC, Tsechpenakis G. Retinal thickness estimation from SD-OCT macular scans. In Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July. IEEE Computer Society. 2015. p. 213-217. 7163852 https://doi.org/10.1109/ISBI.2015.7163852
Hammes, N. ; Racette, L. ; Samuels, B. C. ; Tsechpenakis, G. / Retinal thickness estimation from SD-OCT macular scans. Proceedings - International Symposium on Biomedical Imaging. Vol. 2015-July IEEE Computer Society, 2015. pp. 213-217
@inproceedings{e5a5193dc7aa41e6a38527e88227e7ae,
title = "Retinal thickness estimation from SD-OCT macular scans",
abstract = "Glaucoma, a leading cause of blindness worldwide, can be detected using retinal thicknesses from spectral-domain optical coherence tomography (SD-OCT) scans of the macula. We calculate the desired thickness maps as the distance between the inner-limiting membrane (ILM) and retinal pigmented epithelium (RPE) of the retina. To delineate these two layers, we use a set of two deformable open surfaces that are driven by intensity contrast, while preserving their shape and topology properties, i.e. local surface smoothness and inter-surface distance smoothness. To evaluate our method, qualified graders manually segmented 30 random sections from 20 OCT image stacks, in triplicate; we make comparisons with obtained ground-truth and the clinically tested Heidelberg Spectralis segmentation. We show the superiority of our method with respect to accuracy and average execution time (∼7 secs), validating it as a clinical tool.",
keywords = "early detection of glaucoma, interacting deformable surfaces, Retinal thickness",
author = "N. Hammes and L. Racette and Samuels, {B. C.} and G. Tsechpenakis",
year = "2015",
month = "7",
day = "21",
doi = "10.1109/ISBI.2015.7163852",
language = "English (US)",
isbn = "9781479923748",
volume = "2015-July",
pages = "213--217",
booktitle = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Retinal thickness estimation from SD-OCT macular scans

AU - Hammes, N.

AU - Racette, L.

AU - Samuels, B. C.

AU - Tsechpenakis, G.

PY - 2015/7/21

Y1 - 2015/7/21

N2 - Glaucoma, a leading cause of blindness worldwide, can be detected using retinal thicknesses from spectral-domain optical coherence tomography (SD-OCT) scans of the macula. We calculate the desired thickness maps as the distance between the inner-limiting membrane (ILM) and retinal pigmented epithelium (RPE) of the retina. To delineate these two layers, we use a set of two deformable open surfaces that are driven by intensity contrast, while preserving their shape and topology properties, i.e. local surface smoothness and inter-surface distance smoothness. To evaluate our method, qualified graders manually segmented 30 random sections from 20 OCT image stacks, in triplicate; we make comparisons with obtained ground-truth and the clinically tested Heidelberg Spectralis segmentation. We show the superiority of our method with respect to accuracy and average execution time (∼7 secs), validating it as a clinical tool.

AB - Glaucoma, a leading cause of blindness worldwide, can be detected using retinal thicknesses from spectral-domain optical coherence tomography (SD-OCT) scans of the macula. We calculate the desired thickness maps as the distance between the inner-limiting membrane (ILM) and retinal pigmented epithelium (RPE) of the retina. To delineate these two layers, we use a set of two deformable open surfaces that are driven by intensity contrast, while preserving their shape and topology properties, i.e. local surface smoothness and inter-surface distance smoothness. To evaluate our method, qualified graders manually segmented 30 random sections from 20 OCT image stacks, in triplicate; we make comparisons with obtained ground-truth and the clinically tested Heidelberg Spectralis segmentation. We show the superiority of our method with respect to accuracy and average execution time (∼7 secs), validating it as a clinical tool.

KW - early detection of glaucoma

KW - interacting deformable surfaces

KW - Retinal thickness

UR - http://www.scopus.com/inward/record.url?scp=84944324599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944324599&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2015.7163852

DO - 10.1109/ISBI.2015.7163852

M3 - Conference contribution

AN - SCOPUS:84944324599

SN - 9781479923748

VL - 2015-July

SP - 213

EP - 217

BT - Proceedings - International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -