No-reference based automatic parameter optimization for iterative reconstruction using a novel search space aware crow search algorithm

TL;DR

The paper presents a novel automatic parameter optimization framework for CBCT iterative reconstruction that outperforms manual tuning and existing algorithms, ensuring high-quality images with less radiation exposure.

Contribution

A new fully automatic optimization method using a modified crow search algorithm with innovative search strategies and initialization schemes for improved CBCT reconstruction quality.

Findings

Achieved 4.19% improvement in average fitness over manual settings.

Outperformed existing methods on benchmark quality metrics CHILL@UK and RPI_AXIS.

Demonstrated robustness and effectiveness across multiple datasets and reconstruction algorithms.

Abstract

Iterative reconstruction technique's ability to reduce radiation exposure by using fewer projections has attracted significant attention. However, these methods typically require a precise tuning of several hyperparameters, which can have a major impact on reconstruction quality. Manually setting these parameters is time-consuming and increases the workload for human operators. In this paper, we introduce a novel fully automatic parameter optimization framework that can be applied to a wide range of Cone-beam computed tomography (CBCT) iterative reconstruction algorithms to determine optimal parameters without requiring a reference reconstruction. The proposed method incorporates a modified crow search algorithm (CSA) featuring a superior set-dependent local search mechanism, a search-space-aware global search strategy, and an objective-driven balance between local and global search. Additionally, to ensure an effective initial population, we propose a chaotic diagonal linear uniform initialization scheme that accelerates algorithm convergence. The performance of the proposed framework was evaluated on three imaging machines and four real datasets, as well as three different iterative reconstruction methods with the highest number of tunable parameters, representing the most challenging senario. The results indicate that the proposed method could outperform manual settings and CSA, with an 4.19% improvement in average fitness and 4.89% and 3.82% improvements on CHILL@UK and RPI_AXIS, respectively, which are two benchmark no-reference learning-based quality metrics. In addition, the qualitative results clearly show the superiority of the proposed method by maintaining fine details sharply. The overall performance of the proposed framework across different comparison scenarios demonstrates its effectiveness and robustness across all cases.