Owler, J. and Rockett, P. orcid.org/0000-0002-4636-7727 (2021) Influence of background preprocessing on the performance of deep learning retinal vessel detection. Journal of Medical Imaging, 8 (6). 064001. ISSN 2329-4302
Abstract
Purpose: Segmentation of the vessel tree from retinal fundus images can be used to track changes in the retina, and be an important first step in a diagnosis. Manual segmentation is a time consuming process that is prone to error; effective and reliable automation can alleviate these problems but one of the difficulties is uneven image background which may affect segmentation performance.
Approach: We present a patch-based deep learning framework, based on a modified U-Net architecture, that automatically segments the retinal blood vessels from fundus images. In particular, we evaluate how various preprocessing techniques: images with either no processing, N4 bias field correction, contrast limited adaptive histogram equalization (CLAHE), or a combination of N4 and CLAHE, can compensate for uneven image background and impact final segmentation performance.
Results: We achieved competitive results on three publicly available datasets as a benchmark for our comparisons of pre-processing techniques. In addition, we introduce Bayesian statistical testing which indicates little practical difference (Pr > 0.99) between pre-processing methods apart from the sensitivity metric. In terms of sensitivity and pre-processing, the combination of N4 correction and CLAHE performs better in comparison to unprocessed and N4 pre-processing (Pr > 0.87) but compared to CLAHE alone, the differences are not significant (Pr ≈ 0.38 − 0.88).
Conclusions: We conclude that deep learning is an effective method for retinal vessel segmentation and that CLAHE pre-processing has the greatest positive impact on segmentation performance, with N4 correction helping only in images with extremely inhomogeneous background illumination.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 Society of Photo‑Optical Instrumentation Engineers (SPIE). This is an author-produced version of a paper subsequently published in Journal of Medical Imaging. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | retinal vessel segmentation; deep learning; U-Net; fundus imaging; Bayesian hypothesis testing; image background correction |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Electronic and Electrical Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 28 Oct 2021 15:53 |
Last Modified: | 03 Nov 2021 12:14 |
Status: | Published |
Publisher: | Society of Photo-optical Instrumentation Engineers |
Refereed: | Yes |
Identification Number: | 10.1117/1.JMI.8.6.064001 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:179382 |