Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy

Danuta M. Sampson; David Alonso-Caneiro; Avenell L. Chew; Jonathan La; Danial Roshandel; Yufei Wang; Jane C. Khan; Enid Chelva; Paul G. Stevenson; Fred K. Chen

doi:10.1038/s41598-021-96068-2

Back

Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy

Journal article

Open access

Peer reviewed

Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy

Danuta M. Sampson, David Alonso-Caneiro, Avenell L. Chew, Jonathan La, Danial Roshandel, Yufei Wang, Jane C. Khan, Enid Chelva, Paul G. Stevenson and Fred K. Chen

Scientific Reports, Vol.11, pp.1-9

2021

DOI: https://doi.org/10.1038/s41598-021-96068-2

PMID: 34404857

Files and links (2)

pdf

Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy2.52 MBDownload View

Published VersionCC BY V4.0, Open Access

url

https://doi.org/10.1038/s41598-021-96068-2View

Published Version

Abstract

health care

imaging and sensing

translational research

Adaptive optics flood illumination ophthalmoscopy (AO-FIO) is an established imaging tool in the investigation of retinal diseases. However, the clinical interpretation of AO-FIO images can be challenging due to varied image quality. Therefore, image quality assessment is essential before interpretation. An image assessment tool will also assist further work on improving the image quality, either during acquisition or post processing. In this paper, we describe, validate and compare two automated image quality assessment methods; the energy of Laplacian focus operator (LAPE; not commonly used but easily implemented) and convolutional neural network (CNN; effective but more complex approach). We also evaluate the effects of subject age, axial length, refractive error, fixation stability, disease status and retinal location on AO-FIO image quality. Based on analysis of 10,250 images of 50 × 50 μm size, at 41 retinal locations, from 50 subjects we demonstrate that CNN slightly outperforms LAPE in image quality assessment. CNN achieves accuracy of 89%, whereas LAPE metric achieves 73% and 80% (for a linear regression and random forest multiclass classifier methods, respectively) compared to ground truth. Furthermore, the retinal location, age and disease are factors that can influence the likelihood of poor image quality.

Details

Title: Evaluation of focus and deep learning methods for automated image grading and factors influencing image quality in adaptive optics ophthalmoscopy
Authors: Danuta M. Sampson (Author) - The University of Western Australia
David Alonso-Caneiro (Author) - The University of Western Australia
Avenell L. Chew (Author) - The University of Western Australia
Jonathan La (Author) - The University of Western Australia
Danial Roshandel (Author) - The University of Western Australia
Yufei Wang (Author) - University of Wisconsin–Madison
Jane C. Khan (Author) - Royal Perth Hospital
Enid Chelva (Author) - Sir Charles Gairdner Hospital
Paul G. Stevenson (Author) - The University of Western Australia
Fred K. Chen (Author) - The University of Western Australia
Publication details: Scientific Reports, Vol.11, pp.1-9
Publisher: Nature Publishing Group
Date published: 2021
DOI: 10.1038/s41598-021-96068-2
ISSN: 2045-2322
PMID: 34404857
Copyright note: © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http:// creativecommons.org/ licen ses/ by/4. 0/.
Data Availability: All relevant data are within the paper. The CNN/LAPE algorithm can be available upon request.
Grant note: Ophthalmic Research Institute of Australia (DMS, FKC); Global Ophthalmology Award Program Bayer (FKC); National Health & Medical Research Council (Early Career Fellowship; GNT1054712, Career Development Fellowship; MRF1142962, FKC; Equipment Grant: 37812900, FKC); Retina Australia (FKC); Telethon—Perth Children’s Hospital Research Fund (DMS, DAC, FKC); Rebecca L. Cooper 2018 Project Grant (DAC); Health Department of Western Australia (FKC); McCusker Foundation (FKC); Donations from the Saleeba and Constantine families (FKC).
Organisation Unit: School of Science, Technology and Engineering
Language: English
Record Identifier: 99973593602621
Output Type: Journal article

Metrics

39 Record Views

3 Times Cited - Web of Science

See more details

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Ophthalmology

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites