Evaluation of Particle Swarm Optimisation for Medical Image Segmentation

Mohammad Hashem Ryalat, Daniel Emmens, Mark Hulse, Duncan Bell, Zainab Al-Rahamneh, Stephen Laycock, Mark Fisher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Otsu’s criteria is a popular image segmentation approach that selects a threshold to maximise the inter-class variance of the distribution of intensity levels in the image. The algorithm finds the optimum threshold by performing an exhaustive search, but this is time-consuming, particularly for medical images employing 16-bit quantisation. This paper investigates particle swarm optimisation (PSO), Darwinian PSO and Fractional Order Darwinian PSO to speed up the algorithm. We evaluate the algorithms in medical imaging applications concerned with volume reconstruction, with a particular focus on addressing artefacts due to immobilisation masks, commonly worn by patients undergoing radiotherapy treatment for head-and-neck cancer. We find that the Fractional-Order Darwinian PSO algorithm outperforms other PSO algorithms in terms of accuracy, stability and speed which makes it the favourite choice when the accuracy and time-of-execution are a concern.
Original languageEnglish
Title of host publicationAdvances in Systems Science
Subtitle of host publicationProceedings of the International Conference on Systems Science 2016 (ICSS 2016)
EditorsJerzy Świątek, Jakub M. Tomczak
PublisherSpringer
Pages61-72
Number of pages12
ISBN (Electronic)978-3-319-48944-5
ISBN (Print)978-3-319-48943-8
DOIs
Publication statusPublished - 5 Nov 2016

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer International Publishing
Volume539
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Cite this