Deep learning based retinal OCT segmentation

We look at the recent application of deep learning (DL) methods in automated fine-grained segmentation of spectral domain optical coherence tomography (OCT) images of the retina. We describe a new method combining fully convolutional networks (FCN) with Gaussian Processes for post processing. We rep...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2019-11, Vol.114, p.103445-103445, Article 103445
Main Authors: Pekala, M., Joshi, N., Liu, T.Y. Alvin, Bressler, N.M., DeBuc, D. Cabrera, Burlina, P.
Format: Article
Language:English
Subjects:
Age
Algorithms
Alzheimer's disease
Annotations
Artificial intelligence
Automation
Datasets
Deep learning
Diabetes
Diabetes mellitus
Diabetic retinopathy
Edema
Fully convolutional networks
Gaussian process
Gaussian process regression
Human error
Image processing
Image segmentation
Learning algorithms
Machine learning
Macular degeneration
Methods
Neurodegenerative
OCT segmentation
Optical Coherence Tomography
Performance assessment
Retina
Retinal and vascular diseases
Retinopathy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We look at the recent application of deep learning (DL) methods in automated fine-grained segmentation of spectral domain optical coherence tomography (OCT) images of the retina. We describe a new method combining fully convolutional networks (FCN) with Gaussian Processes for post processing. We report performance comparisons between the proposed approach, human clinicians, and other machine learning (ML) such as graph based approaches. The approach is demonstrated on an OCT dataset consisting of mild non-proliferative diabetic retinopathy from the University of Miami. The method is shown to have performance on par with humans, also compares favorably with the other ML methods, and appears to have as small or smaller mean unsigned error (equal to 1.06), versus errors ranging from 1.17 to 1.81 for other methods, and compared with human error of 1.10.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2019.103445