Evolving Optimised Convolutional Neural Networks for Lung Cancer Classification

Pfeffer, MA; Ling, SH

Evolving Optimised Convolutional Neural Networks for Lung Cancer Classification

Pfeffer, MA Ling, SH

Permalink

Publisher:: MDPI AG
Publication Type:: Journal Article
Citation:: Signals, 2022, 3, (2), pp. 284-295
Issue Date:: 2022-05-05

Recently Added

	Filename	Description	Size
	signals-03-00018.pdf	Published version	1.81 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Pfeffer, MA
dc.contributor.author	Ling, SH
dc.date.accessioned	2022-08-04T01:57:00Z
dc.date.available	2022-08-04T01:57:00Z
dc.date.issued	2022-05-05
dc.identifier.citation	Signals, 2022, 3, (2), pp. 284-295
dc.identifier.issn	2624-6120
dc.identifier.issn	2624-6120
dc.identifier.uri	http://hdl.handle.net/10453/159604
dc.description.abstract	<jats:p>Detecting pulmonary nodules early significantly contributes to the treatment success of lung cancer. Several deep learning models for medical image analysis have been developed to help classify pulmonary nodules. The design of convolutional neural network (CNN) architectures, however, is still heavily reliant on human domain knowledge. Manually designing CNN design solutions has been shown to limit the data’s utility by creating a co-dependency on the creator’s cognitive bias, which urges the development of smart CNN architecture design solutions. In this paper, an evolutionary algorithm is used to optimise the classification of pulmonary nodules with CNNs. The implementation of a genetic algorithm (GA) for CNN architectures design and hyperparameter optimisation is proposed, which approximates optimal solutions by implementing a range of bio-inspired mechanisms of natural selection and Darwinism. For comparison purposes, two manually designed deep learning models, FractalNet and Deep Local-Global Network, were trained. The results show an outstanding classification accuracy of the fittest GA-CNN (91.3%), which outperformed both manually designed models. The findings indicate that GAs pose advantageous solutions for diagnostic challenges, the development of which may to be fully automated in the future using GAs to design and optimise CNN architectures for various clinical applications.</jats:p>
dc.language	en
dc.publisher	MDPI AG
dc.relation.ispartof	Signals
dc.relation.isbasedon	10.3390/signals3020018
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	Evolving Optimised Convolutional Neural Networks for Lung Cancer Classification
dc.type	Journal Article
utslib.citation.volume	3
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Centre for Health Technologies (CHT)
utslib.copyright.status	recently_added	*
dc.date.updated	2022-08-04T01:56:59Z
pubs.issue	2
pubs.publication-status	Published online
pubs.volume	3
utslib.citation.issue	2

Abstract:

Detecting pulmonary nodules early significantly contributes to the treatment success of lung cancer. Several deep learning models for medical image analysis have been developed to help classify pulmonary nodules. The design of convolutional neural network (CNN) architectures, however, is still heavily reliant on human domain knowledge. Manually designing CNN design solutions has been shown to limit the data’s utility by creating a co-dependency on the creator’s cognitive bias, which urges the development of smart CNN architecture design solutions. In this paper, an evolutionary algorithm is used to optimise the classification of pulmonary nodules with CNNs. The implementation of a genetic algorithm (GA) for CNN architectures design and hyperparameter optimisation is proposed, which approximates optimal solutions by implementing a range of bio-inspired mechanisms of natural selection and Darwinism. For comparison purposes, two manually designed deep learning models, FractalNet and Deep Local-Global Network, were trained. The results show an outstanding classification accuracy of the fittest GA-CNN (91.3%), which outperformed both manually designed models. The findings indicate that GAs pose advantageous solutions for diagnostic challenges, the development of which may to be fully automated in the future using GAs to design and optimise CNN architectures for various clinical applications.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/159604