Automatic choroidal segmentation in OCT images using supervised deep learning methods

Autor: Jared Hamwood, Fred K. Chen, Stephen J. Vincent, Jason Kugelman, David Alonso-Caneiro, Scott A. Read, Michael J. Collins
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Support Vector Machine
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
lcsh:Medicine
Image processing
Retinal Pigment Epithelium
01 natural sciences
Article
010309 optics
automatic segmentation
03 medical and health sciences
chemistry.chemical_compound
0302 clinical medicine
Optical coherence tomography
0103 physical sciences
Image Processing
Computer-Assisted
medicine
111300 OPTOMETRY AND OPHTHALMOLOGY
Humans
Segmentation
Computer vision
lcsh:Science
Tomography
optical coherence tomography
Multidisciplinary
medicine.diagnostic_test
Artificial neural network
Choroid
business.industry
Deep learning
lcsh:R
deep learning
Retinal
090300 BIOMEDICAL ENGINEERING
eye diseases
Support vector machine
medicine.anatomical_structure
chemistry
030221 ophthalmology & optometry
lcsh:Q
Neural Networks
Computer
Artificial intelligence
sense organs
business
Biomedical engineering
Tomography
Optical Coherence
Zdroj: Scientific Reports, Vol 9, Iss 1, Pp 1-13 (2019)
Scientific Reports
ISSN: 2045-2322
DOI: 10.1038/s41598-019-49816-4
Popis: 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.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje