Files and links (2)
A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation2.31 MB
Published VersionCC BY V4.0, Open Access
Journal article
A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation
Scientific Reports, Vol.12, pp.1-14
2022
PMID: 36050364
Abstract
Deep learning methods have enabled a fast, accurate and automated approach for retinal layer segmentation in posterior segment OCT images. Due to the success of semantic segmentation methods adopting the U-Net, a wide range of variants and improvements have been developed and applied to OCT segmentation. Unfortunately, the relative performance of these methods is difficult to ascertain for OCT retinal layer segmentation due to a lack of comprehensive comparative studies, and a lack of proper matching between networks in previous comparisons, as well as the use of different OCT datasets between studies. In this paper, a detailed and unbiased comparison is performed between eight U-Net architecture variants across four different OCT datasets from a range of different populations, ocular pathologies, acquisition parameters, instruments and segmentation tasks. The U-Net architecture variants evaluated include some which have not been previously explored for OCT segmentation. Using the Dice coefficient to evaluate segmentation performance, minimal differences were noted between most of the tested architectures across the four datasets. Using an extra convolutional layer per pooling block gave a small improvement in segmentation performance for all architectures across all four datasets. This finding highlights the importance of careful architecture comparison (e.g. ensuring networks are matched using an equivalent number of layers) to obtain a true and unbiased performance assessment of fully semantic models. Overall, this study demonstrates that the vanilla U-Net is sufficient for OCT retinal layer segmentation and that state-of-the-art methods and other architectural changes are potentially unnecessary for this particular task, especially given the associated increased complexity and slower speed for the marginal performance gains observed. Given the U-Net model and its variants represent one of the most commonly applied image segmentation methods, the consistent findings across several datasets here are likely to translate to many other OCT datasets and studies. This will provide significant value by saving time and cost in experimentation and model development as well as reduced inference time in practice by selecting simpler models.
Details
- Title
- A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation
- Authors
- Jason Kugelman (Corresponding Author) - Queensland University of TechnologyJoseph Allman (Author) - Queensland University of TechnologyScott A. Read (Author) - Queensland University of TechnologyStephen J. Vincent (Author) - Queensland University of TechnologyJanelle Tong (Author) - UNSW SydneyMichael Kalloniatis (Author) - UNSW SydneyFred K. Chen (Author) - The University of Western AustraliaMichael J. Collins (Author) - Queensland University of TechnologyDavid Alonso-Caneiro (Author) - Queensland University of Technology
- Publication details
- Scientific Reports, Vol.12, pp.1-14
- Publisher
- Nature Publishing Group
- Date published
- 2022
- DOI
- 10.1038/s41598-022-18646-2
- ISSN
- 2045-2322
- PMID
- 36050364
- Copyright note
- © The Author(s) 2022. 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/ licenses/ by/4. 0/.
- Data Availability
- The healthy, Stargardt disease and widefield datasets analysed during the current study are currently not publicly available. However, the algorithms and code used throughout this study are publicly and readily available at https://github.com/jakugel/unet-variants.
- Grant note
- This work was supported by Ideas Grants and a Fellowship from the Australian National Health and Medical Research Council of Australia [GNT1186915, GNT1116360 (FC) and MRF1142962 (FC)], a scholarship from the Australian Government Research Training Program (JT), and project grants from the Telethon-Perth Children’s Hospital Research Fund (DAC, FC), and the Macular Disease Foundation Australia (FC). Additionally, Guide Dogs NSW/ACT provided a PhD scholarship (JT), salary support (JP and MK) and support clinical service delivery at the Centre for Eye Health.
- Organisation Unit
- School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 99972394702621
- Output Type
- Journal article
Metrics
3 File views/ downloads
79 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Web Of Science research areas
- Radiology, Nuclear Medicine & Medical Imaging
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites