Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography.

Manasavee Lohvithee,Wenjuan Sun,Stephane Chretien,Manuchehr Soleimani

doi:10.3390/s21020591

Manasavee Lohvithee, Wenjuan Sun + Show 2 more

Open Access

https://doi.org/10.3390/s21020591

Copy DOI

Abstract

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.

Highlights

Despite the many advantages of using X-ray computed tomography (XCT) as a tool for medical analysis, the high radiation dose delivered to the patient during clinical exams remains a major concern
Even though iterative methods are proven in many studies to produce good quality images when the projection data is not theoretically sufficient for exact image reconstruction [5,6], their implementations are mathematically more complex and computationally costly than analytical methods. When it comes to the success of limited data XCT, the total variation (TV) image reconstruction methods are shown to be superior in terms of handling the missing data
The adaptive-weighted projection-controlled steepest descent (AwPCSD) algorithm is used as a reconstruction algorithm

Summary

Introduction

Despite the many advantages of using X-ray computed tomography (XCT) as a tool for medical analysis, the high radiation dose delivered to the patient during clinical exams remains a major concern. Even though iterative methods are proven in many studies to produce good quality images when the projection data is not theoretically sufficient for exact image reconstruction [5,6], their implementations are mathematically more complex and computationally costly than analytical methods. When it comes to the success of limited data XCT, the total variation (TV) image reconstruction methods are shown to be superior in terms of handling the missing data. Another concern of the TV-based regularization algorithms is that they are very sensitive to the hyperparameters, which are used to control the weights of the objective functions in the TV optimization problems.

Methods

Results

Conclusion