Deep Learning Based Topology Guaranteed Surface and MME Segmentation of Multiple Sclerosis Subjects from Retinal OCT

Authors

Yufan He, The Johns Hopkins University
Aaron Carass, The Johns Hopkins UniversityFollow
Yihao Liu, The Johns Hopkins UniversityFollow
Bruno Jedynak, Portland State UniversityFollow
Sharon D. Solomon, The Johns Hopkins UniversityFollow
Shiv Saidha, Johns Hopkins School of MedicineFollow
Peter A. Calabresi, Johns Hopkins University School of MedicineFollow
Jerry L. Prince, The Johns Hopkins University

Sponsor

This work was supported by the NIH under NEI grant R01-EY024655 (PI: J.L. Prince) and NINDS grant R01-NS082347 (PI: P.A. Calabresi). This work was also supported in part by NIH NIA R01 AG027161 and NSF Grant DMS 1624776.

Published In

Biomedical Optics Express

Document Type

Article

Publication Date

2019

Subjects

Ultrasound imaging -- Research, Tomography -- Methods

Abstract

Optical coherence tomography (OCT) is a noninvasive imaging modality that can be used to obtain depth images of the retina. Patients with multiple sclerosis (MS) have thinning retinal nerve fiber and ganglion cell layers, and approximately 5% of MS patients will develop microcystic macular edema (MME) within the retina. Segmentation of both the retinal layers and MME can provide important information to help monitor MS progression. Graph-based segmentation with machine learning preprocessing is the leading method for retinal layer segmentation, providing accurate surface delineations with the correct topological ordering. However, graph methods are time-consuming and they do not optimally incorporate joint MME segmentation. This paper presents a deep network that extracts continuous, smooth, and topology-guaranteed surfaces and MMEs. The network learns shape priors automatically during training rather than being hard-coded as in graph methods. In this new approach, retinal surfaces and MMEs are segmented together with two cascaded deep networks in a single feed forward propagation. The proposed framework obtains retinal surfaces (separating the layers) with sub-pixel surface accuracy comparable to the best existing graph methods and MMEs with better accuracy than the state-of-the-art method. The full segmentation operation takes only ten seconds for a 3D volume.

Description

© 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Locate the Document

https://doi.org/10.1364/BOE.10.005042

DOI

10.1364/BOE.10.005042

Persistent Identifier

https://archives.pdx.edu/ds/psu/29583

Citation Details

He, Y., Carass, A., Liu, Y., Jedynak, B. M., Solomon, S. D., Saidha, S., ... & Prince, J. L. (2019). Deep learning based topology guaranteed surface and MME segmentation of multiple sclerosis subjects from retinal OCT. Biomedical Optics Express, 10(10), 5042-5058.