Deakin University
Browse

File(s) under permanent embargo

RC-Net: A Convolutional Neural Network for Retinal Vessel Segmentation

Version 2 2024-06-05, 00:36
Version 1 2022-02-24, 14:34
conference contribution
posted on 2024-06-05, 00:36 authored by TM Khan, Antonio Robles-KellyAntonio Robles-Kelly, SS Naqvi
Over recent years, increasingly complex approaches based on sophisticated convolutional neural network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back to examine the real need for such complexity. We present RC-Net, a fully convolutional network, where the number of filters per layer is optimized to reduce feature overlapping and complexity. We also used skip connections to keep spatial information loss to a minimum by keeping the number of pooling operations in the network to a minimum. Two publicly available retinal vessel segmentation datasets were used in our experiments. In our experiments, RC-Net is quite competitive, outperforming alternatives vessels segmentation methods with two or even three orders of magnitude less trainable parameters.

History

Pagination

606-612

Location

Gold Coast, Australia

Start date

2021-11-29

End date

2021-12-01

ISBN-13

9781665417099

Publication classification

E1 Full written paper - refereed

Editor/Contributor(s)

Zhou J, Salvado O, Sohel F, Borges P, Wang S

Title of proceedings

DICTA 2021 : Proceedings of the Digital Image Computing: Techniques and Application Conference

Event

Digital Image Computing: Techniques and Applications. Conference (2021 : Gold Coast, Australia)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC