Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation.
Dang, Truong; Nguyen, Tien Thanh; Moreno-Garcia, Carlos Francisco; Elyan, Eyad; McCall, John
Dr Thanh Nguyen email@example.com
Dr Carlos Moreno-Garcia firstname.lastname@example.org
Senior Lecturer (A)
Professor Eyad Elyan email@example.com
Professor John McCall firstname.lastname@example.org
In recent years, deep learning has rapidly becomea method of choice for segmentation of medical images. Deep neural architectures such as UNet and FPN have achieved high performances on many medical datasets. However, medical image analysis algorithms are required to be reliable, robust,and accurate for clinical applications which can be difficult to achieve for some single deep learning methods. In this study, we introduce an ensemble of classifiers for semantic segmentation of medical images. The ensemble of classifiers here is a set of various deep learning-based classifiers, aiming to achieve better performance than using a single classifier. We propose a weighted ensemble method in which the weighted sum of segmentation outputs by classifiers is used to choose the final segmentation decision. We use a swarm intelligence algorithm namely Comprehensive Learning Particle Swarm Optimization to optimize the combining weights. Dice coefficient, a popular performance metric for image segmentation, is used as the fitness criteria. Experiments conducted on some medical datasets of the CAMUS competition on cardiographic image segmentation show that our method achieves better results than both the constituent segmentation models and the reported model of the CAMUS competition.
DANG, T., NGUYEN, T.T., MORENO-GARCIA, C.F., ELYAN, E. and MCCALL, J. 2021. Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation. In Proceeding of 2021 IEEE (Institute of electrical and electronics engineers) Congress on evolutionary computation (CEC 2021), 28 June - 1 July 2021, [virtual conference]. Piscataway: IEEE [online], pages 744-751. Available from: https://doi.org/10.1109/CEC45853.2021.9504929
|Conference Name||2021 IEEE (Institute of electrical and electronics engineers) Congress on evolutionary computation (CEC 2021)|
|Conference Location||[virtual conference]|
|Start Date||Jun 28, 2021|
|End Date||Jul 1, 2021|
|Acceptance Date||Feb 23, 2021|
|Online Publication Date||Jul 1, 2021|
|Publication Date||Aug 9, 2021|
|Deposit Date||Aug 16, 2021|
|Publicly Available Date||Aug 16, 2021|
|Publisher||Institute of Electrical and Electronics Engineers|
|Keywords||Image segmentation; Deep neural networks; Ensemble learning; Ensemble method; Particle swarm optimization|
DANG 2021 Weighted ensemble of deep (AAM)
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
You might also like
Assessing the clinicians’ pathway to embed artificial intelligence for assisted diagnostics of fracture detection.
Evolving an optimal decision template for combining classifiers.
Deep heterogeneous ensemble.
Multi-layer heterogeneous ensemble with classifier and feature selection.
Evolving interval-based representation for multiple classifier fusion.