Mr Truong Dang t.dang1@rgu.ac.uk
Research Assistant
Ensemble learning based on classifier prediction confidence and comprehensive learning particle swarm optimisation for medical image segmentation.
Dang, Truong; Nguyen, Tien Thanh; McCall, John; Liew, Alan Wee-Chung
Authors
Dr Thanh Nguyen t.nguyen11@rgu.ac.uk
Senior Research Fellow
Professor John McCall j.mccall@rgu.ac.uk
Director
Alan Wee-Chung Liew
Contributors
Hisao Ishibuchi
Editor
Chee-Keong Kwoh
Editor
Ah-Hwee Tan
Editor
Dipti Srinivasan
Editor
Chunyan Miao
Editor
Anupam Trivedi
Editor
Keeley Crockett
Editor
Abstract
Segmentation, a process of partitioning an image into multiple segments to locate objects and boundaries, is considered one of the most essential medical imaging process. In recent years, Deep Neural Networks (DNN) have achieved many notable successes in medical image analysis, including image segmentation. Due to the fact that medical imaging applications require robust, reliable results, it is necessary to devise effective DNN models for medical applications. One solution is to combine multiple DNN models in an ensemble system to obtain better results than using each single DNN model. Ensemble learning is a popular machine learning technique in which multiple models are combined to improve the final results and has been widely used in medical image analysis. In this paper, we propose to measure the confidence in the prediction of each model in the ensemble system and then use an associate threshold to determine whether the confidence is acceptable or not. A segmentation model is selected based on the comparison between the confidence and its associated threshold. The optimal threshold for each segmentation model is found by using Comprehensive Learning Particle Swarm Optimisation (CLPSO), a swarm intelligence algorithm. The Dice coefficient, a popular performance metric for image segmentation, is used as the fitness criteria. The experimental results on three medical image segmentation datasets confirm that our ensemble achieves better results compared to some well-known segmentation models.
Citation
DANG, T., NGUYEN, T.T., MCCALL, J. and LIEW, A.W.-C. 2022. Ensemble learning based on classifier prediction confidence and comprehensive learning particle swarm optimisation for medical image segmentation. In Ishibuchi, H., Kwoh, C.-K., Tan, A.-H., Srinivasan, D., Miao, C., Trivedi, A. and Crockett, K. (eds.) Proceedings of the 2022 IEEE Symposium series on computational intelligence (SSCI 2022), 4-7 December 2022, Singapore. Piscataway: IEEE [online], pages 269-276. Available from: https://doi.org/10.1109/SSCI51031.2022.10022114
Conference Name | 2022 IEEE Symposium series on computational intelligence (SSCI 2022) |
---|---|
Conference Location | Singapore, Singapore |
Start Date | Dec 4, 2022 |
End Date | Dec 7, 2022 |
Acceptance Date | Sep 1, 2022 |
Online Publication Date | Dec 7, 2022 |
Publication Date | Jan 30, 2023 |
Deposit Date | Feb 2, 2023 |
Publicly Available Date | Feb 2, 2023 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 269-276 |
Book Title | Proceedings of the 2022 IEEE Symposium series on computational intelligence (SSCI 2022) |
ISBN | 9781665487689 |
DOI | https://doi.org/10.1109/SSCI51031.2022.10022114 |
Keywords | Image segmentation; Deep learning; Ensemble selection; Ensemble method; Particle swarm optimization |
Public URL | https://rgu-repository.worktribe.com/output/1871687 |
Files
DANG 2022 Ensemble learning based (AAM)
(643 Kb)
PDF
Copyright Statement
© 2022 IEEE.
You might also like
Two-layer ensemble of deep learning models for medical image segmentation. [Article]
(2024)
Journal Article
A weighted ensemble of regression methods for gross error identification problem.
(2023)
Conference Proceeding
Towards explainable metaheuristics: feature extraction from trajectory mining.
(2023)
Journal Article
Explaining a staff rostering genetic algorithm using sensitivity analysis and trajectory analysis.
(2023)
Conference Proceeding
A comparative study of anomaly detection methods for gross error detection problems.
(2023)
Journal Article
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search