Deakin University
Browse

File(s) under permanent embargo

Shallow Vessel Segmentation Network for Automatic Retinal Vessel Segmentation

Version 2 2024-06-05, 07:19
Version 1 2020-10-13, 15:41
conference contribution
posted on 2024-06-05, 07:19 authored by Tariq M Khan, Faizan Abdullah, Syed S Naqvi, Muhammad Arsalan, Muhamamd Aurangzeb Khan
Accurate automatic segmentation of the retinal vessels is crucial for early detection and diagnosis of vision-threatening retinal diseases. This paper presents a lightweight convolutional neural network termed as Shallow Vessel Segmentation Network (SVSN) for vessel segmentation. To achieve semantic segmentation encoder-decoder structures embedded with spatial pyramid pooling modules are used. After checking the input features with pooling through multiple fields of view and rates, it becomes easy for the erstwhile networks to encode multi-scale contextual information. While boundaries for sharper objects are captured by the prevalent networks. Moreover, the need for pre- and post-processing steps are eradicated. Consequently, the detection accuracy is significantly improved with scores of 0.9625 and 0.9645 on DRIVE and STARE datasets respectively.

History

Pagination

1-7

Location

Online from Glasgow, Scotland

Start date

2020-07-19

End date

2020-07-24

ISBN-13

978-1-7281-6926-2

Language

eng

Publication classification

E1 Full written paper - refereed

Title of proceedings

IJCNN 2020 : Proceedings of the 2020 International Joint Conference on Neural Networks

Event

IEEE Computational Intelligence Society. Conference (2020 : Online from Glasgow, Scotland)

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