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

Poorya MohammadiNasab; Ander Biguri; Philipp Steininger; Peter Keuschnigg; Lukas Lamminger; Agnieszka Lach; S M Ragib Shahriar Islam; Anna Breger

cs.CVApr 6, 2026

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

Authors: Poorya MohammadiNasab, Ander Biguri, Philipp Steininger, Peter Keuschnigg, Lukas Lamminger, Agnieszka Lach, S M Ragib Shahriar Islam, Anna Breger, +4 more

Organizations: Department of Medicine, Danube Private University (DPU), Krems, Austria · Center for Medical Physics and Biomedical Engineering, Medical University Vienna, Vienna, Austria · Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom · MedPhoton GmbH, Salzburg, Austria · Austrian Center for Medical Innovation and Technology (ACMIT), Wiener Neustadt, Austria · Faculty of Mathematics, University of Vienna, Vienna, Austria

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.

Figures & tables

Figure 1: Reconstruction results of (A) optimized parameter set and (B and C) small variation of optimized parameters in AwPCSD algorithm.

Figure 2: Overall automatic parameter optimization framework

$Parameter$	$Algorithm$	$Description$	$Valuerange$ [ $min,max,step$ ]
$Max\_iter$	ASD-POCS AwPCSD PICCS	Maximum algorithm iterations	[5, 50, 1] 46 values
$TV\_iter$	ASD-POCS AwPCSD PICCS	Number of TV minimization steps per iteration	[5, 50, 1] 46 values
$\epsilon$	ASD-POCS AwPCSD PICCS	Data inconsistency tolerance parameter	[50, 1500, 10] 146 values
$\alpha$	ASD-POCS PICCS	Initial steepest descent step size	[0.0001, 0.1, 0.0001] 1000 values
$\alpha\_red$	ASD-POCS PICCS	Reduction factor of steepest descent step size	[0.9, 0.99, 0.01] 10 values
$\lambda$	ASD-POCS AwPCSD PICCS	Sets the value of the hyperparameter for the SART iterations	[0.9, 0.99, 0.01] 10 values

Table 1: Tuneable Hyperparameters of ASD-POCS, AwPCSD, and PICCS

Figure 3: (A) Random Initialization, (B) LHS initialization, (C) DLU initialization, and (D) Proposed chaotic DLU initialization

Figure 4: Weight map of search space after running the proposed SSA-CSA method to optimize ASD-POCS for a dataset. Each plot corresponds to one hyperparameter of the algorithm and indicates the weight of each value.

	Classic metrics			Learning-Based Models
	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
SNR Fitness	1.34170	0.15460	4.32603	2.76648	0.54072
Laplacian Fitness	1.07590	0.23580	4.08952	2.50858	0.54818
HFER Fitness	0.90320	0.30440	3.90522	2.31846	0.58378
SNR+Laplacian Fitness	0.94390	0.28710	3.94965	2.79979	0.54388
Proposed fitness SNR+HFER	0.71330	0.37350	3.80060	3.08410	0.73592

Table 2: Performance of different fitness functions.

Figure 5: Qualitative results of (A) SNR, (B) Laplacian, (C) HFER, (D) SNR-Laplacian, and (E) proposed fitness functions

	Classic metrics			Learning-Based Models
	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
Random initialization	0.90571 $\pm$ 0.0387	0.36678 $\pm$ 0.0069	3.62238 $\pm$ 0.0178	2.94742 $\pm$ 0.1459	0.74609 $\pm$ 0.0451
LHS initialization	0.86339 $\pm$ 0.0377	0.36516 $\pm$ 0.0048	3.66753 $\pm$ 0.0113	2.87278 $\pm$ 0.1182	0.72683 $\pm$ 0.0282
DLU initialization	0.95001 $\pm$ 0.0184	0.32673 $\pm$ 0.0052	3.76655 $\pm$ 0.0052	02.82699 $\pm$ 0.0714	0.69795 $\pm$ 0.0199
Proposed initialization	0.899799 $\pm$ 0.0210	0.380161 $\pm$ 0.0029	3.56722 $\pm$ 0.0095	3.10646 $\pm$ 0.1017	0.74726 $\pm$ 0.0226

Table 3: Performance of the proposed SSA-CSA with different initialization methods.

Figure 6: Fitness convergence using different initialization methods.

			Classic metrics		Learning-Based Models
	Algorithm	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
	ASD-POCS	0.73021	0.35616	3.85591	3.00685	0.70177
Manual Setting [ 38 ]	AwPCSD	0.73533	0.36053	3.82957	3.07818	0.69942
	ASD-POCS	1.00030	0.26501	4.00725	2.59235	0.65613
CSA	AwPCSD	0.75690	0.35570	3.82416	3.25605	0.70814
	ASD-POCS	0.71330	0.37350	3.80060	3.08410	0.73592

Table 4: Performance of the different optimization methods with two different reconstruction algorithm on SophiaBead dataset.

Figure 7: Qualitative results of Manual, CSA, and SSA-CSA on (A-C) ASD-POCS, and (E-F) AwPCSD reconstruction on SophiaBeads dataset

		Reference-based metrics
		PSNR	FSIM	FSIMc	$Haarpsi_{MED}$	VSI	VIF	DISTS	LPIPS
Range		[0 - inf] dB	[0 - 1]	[0 - 1]	[0 - 1]	[0 - 1]	[0 - 1]	[0 - 1]	[0 - inf]
Value assessment		$\Uparrow$	$\Uparrow$	$\Uparrow$	$\Uparrow$	$\Uparrow$	$\Uparrow$	$\Downarrow$	$\Downarrow$
	SNR	28.06274	0.82860	0.81270	0.22222	0.98467	0.11960	0.37901	0.39808
	Laplacian	29.11234	0.83340	0.82150	0.22854	0.98900	0.23730	0.35384	0.35896
	HFER	30.46449	0.83930	0.83140	0.26012	0.99179	0.39130	0.33722	0.32110

Table 5: Full-reference image quality assessment results on the SophiaBeads dataset using the ASD-POCS algorithm. In the value assessment row,

\Uparrow

indicates higher is better, and

\Downarrow

indicates lower is better.

		Classic metrics			Learning-Based Models
	Algorithm	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
	ASD-POCS	2.19400	0.42660	2.89935	2.19328	0.61135
Manual setting	AwPCSD	1.67370	0.49310	2.69929	2.47366	0.62196
	ASD-POCS	1.99470	0.46820	2.74403	2.53246	0.62230
CSA	AwPCSD	1.64170	0.49730	2.68854	2.46662	0.61846
	ASD-POCS	1.83100	0.50060	2.62960	2.48891	0.63080

Table 6: Performance of the different optimization methods with two different reconstruction algorithm on LinePairs dataset.

Figure 8: Qualitative results of Manual, CSA, and SSA-CSA on (A-C) ASD-POCS, and (E-F) AwPCSD reconstruction on LinePairs dataset

Figure 9: ASD-POCS reconstruction results on Thorax data using different optimization approaches

Figure 10: AwPCSD reconstruction results on Thorax data using different optimization approaches

			Classic metrics		Learning-Based Models
	Algorithm	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
	ASD-POCS	1.26260	0.31520	3.63601	2.61885	0.60266
Manual Setting	AwPCSD	1.28770	0.29850	3.70035	2.42057	0.58130
	ASD-POCS	1.22730	0.32620	3.60246	2.57055	0.58787
CSA	AwPCSD	1.24460	0.30340	3.69713	2.62096	0.57254
	ASD-POCS	1.10710	0.37380	3.45018	2.74691	0.63154

Table 7: Performance of the different optimization methods with two different reconstruction algorithm on Thorax dataset.

	Classic metrics			Learning-Based Models
	SNR	HFER	Fitness	CHILL@UK	RPI_AXIS
Manual setting	1.69057	0.33843	3.39111	2.42896	0.66923
CSA	1.53696	0.40155	3.14846	2.62561	0.69504
SSA-CSA	1.28064	0.44485	3.04477	2.67673	0.70178

Table 8: Performance of different optimization methods with PICCS algorithm on brain phantom

Figure 11: PICCS reconstruction results on Brain data using different optimization approaches. First row indicates the prior knowledge for all algorithms.

	Fitness Correlation
	CHILL@UK	RPI_AXIS
SophiaBeads	-0.93758	-0.94000
LinePairs	-0.86564	-0.81844
Thorax data	-0.77732	-0.91589
Brain data	-0.99507	-0.99516

Table 9: Pearson correlation of proposed fitness and different learning-based quality assessments for different datasets.

Section	Algorithm	Experiment	$Max\_iter$	$TV\_iter$	$\epsilon$	$\alpha$	$\alpha_{red}$	$\lambda$	$\lambda_{red}$	$r\_max$	$\delta$
		SNR	5	6	1072	0.1000	0.950	0.924	0.910	0.900	-
		Laplacian	8	12	83	0.0002	0.940	0.997	0.908	0.980	-
		HFER	15	10	56	0.0001	0.997	0.971	0.938	0.900	-
5.2.1 Fitness functions	ASD-POCS	SNR + Laplacian	48	9	309	0.0001	0.975	0.916	0.929	0.900	-
		Random	50	25	347	0.0217	0.934	0.999	0.944	0.904	-
		LHS	42	20	983	0.0135	0.956	0.983	0.967	0.950	-

Table 10: Final solution of all performed experiments with different scenarios and setups

Explore similar work

Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials
Sep 10, 2026Jiaqi Zou, David Fenwick, Vahid Tarokh +6Computed Tomography
Department of Electrical and Computer Engineering, Duke University, Durham, NC 27705 USA · Department of Radiology and Medical Physics Graduate Program, Duke University, Durham, NC 27705 USA · Oak Ridge National Laboratory, Oak Ridge, TN 37830 USA +3
Enabling self-supervised learned primal dual with Noise2Inverse
Jun 25, 2026Antti Sällinen, Siiri Rautio, Santeri Kaupinmäki +1Self-Supervised Learning Image Reconstruction
Research Unit of Mathematical Sciences, University of Oulu, Finland · Department of Mathematics and Information Science, Josai University, Japan · Department of Computer Science, University College London, United Kingdom
SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography
Jul 4, 2026Shunta Nonaga, Koji Tabata, Junya Honda +3Sparse-View CT Reconstruction Adaptive Sampling
Graduate School of Chemical Sciences and Engineering, Hokkaido University, Kita 13 Nishi 8, Kita-ku, Sapporo, Hokkaido 060-8628, Japan. · Research Center of Mathematics for Social Creativity, Research Institute for Electronic Science, Hokkaido University, Kita 20 Nishi 10, Kita-ku, Sapporo, Hokkaido 001-0020, Japan · Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido University, Kita 21 Nishi 10, Kita-ku, Sapporo, Hokkaido 001-0021, Japan. +7

Sep 10, 2026J/K move · Enter open · S save

Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials

Jiaqi Zou, David Fenwick, Vahid Tarokh, Nicholas Felice+5

Department of Electrical and Computer Engineering, Duke University, Durham, NC 27705 USA · Department of Radiology and Medical Physics Graduate Program, Duke University, Durham, NC 27705 USA · Oak Ridge National Laboratory, Oak Ridge, TN 37830 USA+3

Computed Tomography

Open paper AskPDF arXiv

Protocol optimization in computed tomography (CT) aims to improve diagnostic image quality while reducing radiation dose, but the interdependence of acquisition and reconstruction parameters makes exhaustive testing impractical. We propose a virtual imaging trial framework with reinforcement learning for efficient CT protocol optimization. Sixty-three computational human models with liver lesions were imaged using a validated CT simulator across 468 combinations of acquisition and reconstruction parameters, including tube voltage, tube current, reconstruction kernel, slice thickness, and pixel size. The optimization objective balanced liver lesion detectability, quantified by detectability index d-prime, against radiation dose. A Proximal Policy Optimization agent was trained and conditioned on patient-specific CT localizer embeddings derived from a pretrained vision transformer. On held-out patients, evaluating only 8 protocols per patient, about 2% of exhaustive testing, recovered 98.2% of the exhaustive-search oracle objective. With no patient-specific simulation, surrogate scoring alone achieved 89.7% recovery. Conditioning on the localizer improved zero-simulation recovery by 10.7 percentage points over the localizer-blind policy (paired 95% CI 2.9-19.5; p=0.02). These results show that the proposed framework can substantially reduce exhaustive protocol testing while enabling task-based, dose-aware protocol selection before the diagnostic scan.

Abstract

Explore similar work

Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials

Enabling self-supervised learned primal dual with Noise2Inverse

SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography