OCT-OCTA Segmentation: a Novel Framework and an Application to Segment Bruch's Membrane in the Presence of Drusen

Schottenhamml J, Moult EM, Novais EA, Kraus M, Lee B, Choi W, Ploner S, Husvogt L, Lu CD, Yiu P, Rosenfeld P, Duker JS, Maier A, Waheed NK, Fujimoto JG (2017)

Publication Language: English

Publication Type: Conference contribution, Abstract of a poster

Publication year: 2017

Publisher: C.V. Mosby Co

Book Volume: 58

Pages Range: 645

Edition: 8

Conference Proceedings Title: Investigative Ophthalmology & Visual Science

Event location: Baltimore, MD, USA

URI: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Schottenhamml17-OSA.pdf

Abstract

Purpose : We present a novel framework for segmenting optical coherence tomography (OCT) and OCT angiography (OCTA) that jointly uses structural and angiographic information. We term this new paradigm “OCT-OCTA segmentation,” and demonstrate its utility by segmenting Bruch’s membrane (BM) in the presence of drusen.

Methods : We developed an automatic OCT-OCTA graph-cut algorithm for BM segmentation. Our algorithm’s performance was quantitatively validated by comparing it with manual segmentation in 7 eyes (6 patients; 73.8±5.7 y/o) with drusen. The algorithm was also qualitatively assessed in healthy eyes (n=13), eyes with diabetic retinopathy (n=21), early/intermediate age-related macular degeneration (AMD) (n=14), exudative AMD (n=5), geographic atrophy (GA) (n=6), and polypoidal choroidal vasculopathy (n=7).

Results : The absolute pixel-wise error between the manual and automatic segmentations had the following values: mean: 4.5±0.89um; 1st Quartile: 1.9±1.35um; 2nd Quartile: 3.9±1.90um; and 3rd Quartile: 6.3±2.67. This corresponds to a mean absolute error smaller than the optical axial resolution of our OCT system (~8-9um). In all other tested eyes, qualitative visual inspection showed BM contours that were deemed suitably accurate for use in forming en face OCT(A) projections. The algorithm’s poorest results occurred in GA patients with large areas of atrophy.

Conclusions : By leveraging both structural and angiographic information we showed that OCT-OCTA segmentation is likely to be a widely useful framework for segmenting ocular structures

Authors with CRIS profile

Related research project(s)

Involved external institutions

Massachusetts Institute of Technology (MIT) United States (USA) (US) Tufts University United States (USA) (US) University of Miami United States (USA) (US) Tufts Medical Center United States (USA) (US)

How to cite

APA:

Schottenhamml, J., Moult, E.M., Novais, E.A., Kraus, M., Lee, B., Choi, W.,... Fujimoto, J.G. (2017, June). OCT-OCTA Segmentation: a Novel Framework and an Application to Segment Bruch's Membrane in the Presence of Drusen. Poster presentation at ARVO Annual Meeting 2017, Baltimore, MD, USA, US.

MLA:

Schottenhamml, Julia, et al. "OCT-OCTA Segmentation: a Novel Framework and an Application to Segment Bruch's Membrane in the Presence of Drusen." Presented at ARVO Annual Meeting 2017, Baltimore, MD, USA C.V. Mosby Co, 2017.

BibTeX: Download