Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography
In this paper, a computer-aided training method for hyperparameter selection of limited data X-ray computed tomography (XCT) reconstruction was proposed. The proposed method employed the ant colony optimisation (ACO) approach to assist in hyperparameter selection for the adaptive-weighted projection...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/2/591 |
_version_ | 1797411010459467776 |
---|---|
author | Manasavee Lohvithee Wenjuan Sun Stephane Chretien Manuchehr Soleimani |
author_facet | Manasavee Lohvithee Wenjuan Sun Stephane Chretien Manuchehr Soleimani |
author_sort | Manasavee Lohvithee |
collection | DOAJ |
description | In this paper, a computer-aided training method for hyperparameter selection of limited data X-ray computed tomography (XCT) reconstruction was proposed. The proposed method employed the ant colony optimisation (ACO) approach to assist in hyperparameter selection for the adaptive-weighted projection-controlled steepest descent (AwPCSD) algorithm, which is a total-variation (TV) based regularisation algorithm. During the implementation, there was a colony of artificial ants that swarm through the AwPCSD algorithm. Each ant chose a set of hyperparameters required for its iterative CT reconstruction and the correlation coefficient (CC) score was given for reconstructed images compared to the reference image. A colony of ants in one generation left a pheromone through its chosen path representing a choice of hyperparameters. Higher score means stronger pheromones/probabilities to attract more ants in the next generations. At the end of the implementation, the hyperparameter configuration with the highest score was chosen as an optimal set of hyperparameters. In the experimental results section, the reconstruction using hyperparameters from the proposed method was compared with results from three other cases: the conjugate gradient least square (CGLS), the AwPCSD algorithm using the set of arbitrary hyperparameters and the cross-validation method.The experiments showed that the results from the proposed method were superior to those of the CGLS algorithm and the AwPCSD algorithm using the set of arbitrary hyperparameters. Although the results of the ACO algorithm were slightly inferior to those of the cross-validation method as measured by the quantitative metrics, the ACO algorithm was over 10 times faster than cross—Validation. The optimal set of hyperparameters from the proposed method was also robust against an increase of noise in the data and can be applicable to different imaging samples with similar context. The ACO approach in the proposed method was able to identify optimal values of hyperparameters for a dataset and, as a result, produced a good quality reconstructed image from limited number of projection data. The proposed method in this work successfully solves a problem of hyperparameters selection, which is a major challenge in an implementation of TV based reconstruction algorithms. |
first_indexed | 2024-03-09T04:38:49Z |
format | Article |
id | doaj.art-2869511b1d094f5e8c5a32beffc5ec01 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T04:38:49Z |
publishDate | 2021-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-2869511b1d094f5e8c5a32beffc5ec012023-12-03T13:24:21ZengMDPI AGSensors1424-82202021-01-0121259110.3390/s21020591Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed TomographyManasavee Lohvithee0Wenjuan Sun1Stephane Chretien2Manuchehr Soleimani3Department of Nuclear Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, ThailandNational Physical Laboratory (NPL), Teddington, Middlesex TW11 0LW, UKNational Physical Laboratory (NPL), Teddington, Middlesex TW11 0LW, UKEngineering Tomography Laboratory (ETL), University of Bath, Bath BA2 7AY, UKIn this paper, a computer-aided training method for hyperparameter selection of limited data X-ray computed tomography (XCT) reconstruction was proposed. The proposed method employed the ant colony optimisation (ACO) approach to assist in hyperparameter selection for the adaptive-weighted projection-controlled steepest descent (AwPCSD) algorithm, which is a total-variation (TV) based regularisation algorithm. During the implementation, there was a colony of artificial ants that swarm through the AwPCSD algorithm. Each ant chose a set of hyperparameters required for its iterative CT reconstruction and the correlation coefficient (CC) score was given for reconstructed images compared to the reference image. A colony of ants in one generation left a pheromone through its chosen path representing a choice of hyperparameters. Higher score means stronger pheromones/probabilities to attract more ants in the next generations. At the end of the implementation, the hyperparameter configuration with the highest score was chosen as an optimal set of hyperparameters. In the experimental results section, the reconstruction using hyperparameters from the proposed method was compared with results from three other cases: the conjugate gradient least square (CGLS), the AwPCSD algorithm using the set of arbitrary hyperparameters and the cross-validation method.The experiments showed that the results from the proposed method were superior to those of the CGLS algorithm and the AwPCSD algorithm using the set of arbitrary hyperparameters. Although the results of the ACO algorithm were slightly inferior to those of the cross-validation method as measured by the quantitative metrics, the ACO algorithm was over 10 times faster than cross—Validation. The optimal set of hyperparameters from the proposed method was also robust against an increase of noise in the data and can be applicable to different imaging samples with similar context. The ACO approach in the proposed method was able to identify optimal values of hyperparameters for a dataset and, as a result, produced a good quality reconstructed image from limited number of projection data. The proposed method in this work successfully solves a problem of hyperparameters selection, which is a major challenge in an implementation of TV based reconstruction algorithms.https://www.mdpi.com/1424-8220/21/2/591hyperparameter tuningtotal variation (TV) regularizationiterative reconstructionant colony optimizationlimited data X-ray CTcomputer-aided hyperparameter selection |
spellingShingle | Manasavee Lohvithee Wenjuan Sun Stephane Chretien Manuchehr Soleimani Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography Sensors hyperparameter tuning total variation (TV) regularization iterative reconstruction ant colony optimization limited data X-ray CT computer-aided hyperparameter selection |
title | Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography |
title_full | Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography |
title_fullStr | Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography |
title_full_unstemmed | Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography |
title_short | Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography |
title_sort | ant colony based hyperparameter optimisation in total variation reconstruction in x ray computed tomography |
topic | hyperparameter tuning total variation (TV) regularization iterative reconstruction ant colony optimization limited data X-ray CT computer-aided hyperparameter selection |
url | https://www.mdpi.com/1424-8220/21/2/591 |
work_keys_str_mv | AT manasaveelohvithee antcolonybasedhyperparameteroptimisationintotalvariationreconstructioninxraycomputedtomography AT wenjuansun antcolonybasedhyperparameteroptimisationintotalvariationreconstructioninxraycomputedtomography AT stephanechretien antcolonybasedhyperparameteroptimisationintotalvariationreconstructioninxraycomputedtomography AT manuchehrsoleimani antcolonybasedhyperparameteroptimisationintotalvariationreconstructioninxraycomputedtomography |