pith. sign in

arxiv: 2604.06246 · v1 · submitted 2026-04-06 · 💻 cs.CV

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
show 4 more authors
Clemens Karner Carola-Bibiane Sch\"onlieb Wolfgang Birkfellner Sepideh Hatamikia
This is my paper

Pith reviewed 2026-05-10 18:40 UTC · model grok-4.3

classification 💻 cs.CV
keywords automatic parameter optimizationiterative reconstructioncrow search algorithmcone-beam CTno-reference image qualityCBCThyperparameter tuning
0
0 comments X

The pith

A modified crow search algorithm automatically optimizes parameters for iterative CBCT reconstruction without needing reference images.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a fully automatic framework to tune the many hyperparameters in cone-beam CT iterative reconstruction algorithms. These methods can lower radiation dose by using fewer projections, but their output quality depends heavily on precise parameter choices that are normally set by hand. The authors enhance the crow search algorithm with a set-dependent local search, a search-space-aware global search, an objective-driven balance between the two, and a chaotic initialization scheme to generate a strong starting population. The result is evaluated on four real datasets from three machines and three different reconstruction methods, showing consistent gains over both manual tuning and the unmodified algorithm when scored by two no-reference quality metrics.

Core claim

The proposed framework uses a modified crow search algorithm with a superior set-dependent local search mechanism, a search-space-aware global search strategy, and an objective-driven balance between local and global search, together with a chaotic diagonal linear uniform initialization. Applied to three iterative reconstruction methods on four real datasets from three imaging machines, it outperforms manual settings and standard CSA by 4.19 percent in average fitness, 4.89 percent on CHILL@UK, and 3.82 percent on RPI_AXIS, while preserving fine details more sharply.

What carries the argument

The search-space-aware crow search algorithm equipped with set-dependent local search, search-space-aware global search, objective-driven local-global balance, and chaotic diagonal linear uniform initialization.

If this is right

  • Reconstruction quality improves without requiring an expert operator to tune parameters for each new dataset or machine.
  • Fewer projections can be used while still obtaining usable images, directly lowering patient radiation exposure.
  • The same framework works across multiple reconstruction algorithms and imaging systems without modification.
  • Fine anatomical details remain sharper than with either manual tuning or the baseline search algorithm.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Embedding the optimizer inside scanner control software could allow per-scan adaptation rather than fixed presets.
  • The approach might be tested on other tomographic modalities such as fan-beam CT or tomosynthesis to check transferability.
  • Replacing the no-reference metrics with faster surrogate models could reduce the overall computation time of the search.

Load-bearing premise

The two no-reference learning-based quality metrics accurately stand in for true reconstruction quality when no ground-truth reference is available.

What would settle it

Apply the same optimization to synthetic or phantom data that also has high-quality reference reconstructions available, then compare whether the no-reference-optimized parameters produce images that match or exceed the quality achieved by reference-based parameter search.

Figures

Figures reproduced from arXiv: 2604.06246 by Agnieszka Lach, Ander Biguri, Anna Breger, Carola-Bibiane Sch\"onlieb, Clemens Karner, Lukas Lamminger, Peter Keuschnigg, Philipp Steininger, Poorya MohammadiNasab, Sepideh Hatamikia, S M Ragib Shahriar Islam, Wolfgang Birkfellner.

Figure 1
Figure 1. Figure 1: Reconstruction results of (A) optimized parameter set and (B and C) small [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall automatic parameter optimization framework [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: (A) Random Initialization, (B) LHS initialization, (C) DLU initialization, and [PITH_FULL_IMAGE:figures/full_fig_p014_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Weight map of search space after running the proposed SSA-CSA method to [PITH_FULL_IMAGE:figures/full_fig_p019_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results of (A) SNR, (B) Laplacian, (C) HFER, (D) SNR-Laplacian, [PITH_FULL_IMAGE:figures/full_fig_p026_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Fitness convergence using different initialization methods. [PITH_FULL_IMAGE:figures/full_fig_p027_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative results of Manual, CSA, and SSA-CSA on (A-C) ASD-POCS, and [PITH_FULL_IMAGE:figures/full_fig_p028_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Qualitative results of Manual, CSA, and SSA-CSA on (A-C) ASD-POCS, and [PITH_FULL_IMAGE:figures/full_fig_p030_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: ASD-POCS reconstruction results on Thorax data using different optimization [PITH_FULL_IMAGE:figures/full_fig_p031_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: AwPCSD reconstruction results on Thorax data using different optimization [PITH_FULL_IMAGE:figures/full_fig_p032_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: PICCS reconstruction results on Brain data using different optimization ap [PITH_FULL_IMAGE:figures/full_fig_p035_11.png] view at source ↗
read the original 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The paper proposes a fully automatic parameter optimization framework for iterative reconstruction algorithms in cone-beam CT (CBCT) that uses a modified crow search algorithm (CSA). The modifications include a set-dependent local search mechanism, a search-space-aware global search strategy, an objective-driven balance between local and global search, and a chaotic diagonal linear uniform initialization scheme. The framework optimizes hyperparameters of three iterative reconstruction methods on four real CBCT datasets from three imaging machines by maximizing two no-reference learning-based quality metrics (CHILL@UK and RPI_AXIS) as fitness functions, without requiring reference reconstructions. Results claim a 4.19% average fitness improvement over manual settings and standard CSA, with specific gains of 4.89% and 3.82% on the two metrics, plus qualitative visual superiority in preserving fine details.

Significance. If the no-reference metrics prove to be reliable proxies for reconstruction quality, the approach could meaningfully reduce the manual tuning burden for CBCT iterative methods, which is a practical bottleneck in clinical and research settings. The algorithmic modifications to CSA and the initialization strategy offer targeted improvements for high-dimensional search spaces typical of these reconstruction problems. The evaluation across multiple machines, datasets, and methods provides some evidence of robustness, but the absence of ground-truth validation substantially weakens the ability to claim genuine quality gains.

major comments (2)
  1. [Evaluation / Results (as summarized in abstract)] The central evaluation (described in the abstract and results) tests the method exclusively on four real CBCT datasets that lack ground truth. No phantom, simulated, or controlled experiments are reported that would allow direct comparison of the optimized parameters against reference-based metrics such as PSNR, SSIM, or task-specific detectability indices. Without this link, the reported 4.19% fitness gain and claims of superior detail preservation rest entirely on the unverified assumption that higher CHILL@UK and RPI_AXIS scores indicate better fidelity.
  2. [Method description and results comparison] The paper does not provide an ablation study isolating the contribution of each proposed CSA modification (set-dependent local search, search-space-aware global search, objective-driven balance) or the chaotic initialization scheme. It is therefore unclear which components drive the observed improvements versus the baseline CSA, undermining the claim that the full set of modifications is necessary for the reported gains.
minor comments (3)
  1. [Abstract] Abstract contains grammatical errors: 'an 4.19%' should read 'a 4.19%' and 'senario' should be 'scenario'.
  2. [Method / Experimental setup] The specific numerical ranges and discretization of the search space for each tunable parameter in the three reconstruction methods are not stated, making it difficult to assess the practical scope of the 'search-space-aware' strategy.
  3. [Abstract and introduction] The two no-reference metrics (CHILL@UK and RPI_AXIS) are referred to as 'benchmark' without citations to their original publications or any discussion of their known limitations or correlation with perceptual or diagnostic quality.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thorough review and insightful comments on our manuscript. We address each major comment below and outline the revisions we will make to improve the paper.

read point-by-point responses

  1. Referee: [Evaluation / Results (as summarized in abstract)] The central evaluation (described in the abstract and results) tests the method exclusively on four real CBCT datasets that lack ground truth. No phantom, simulated, or controlled experiments are reported that would allow direct comparison of the optimized parameters against reference-based metrics such as PSNR, SSIM, or task-specific detectability indices. Without this link, the reported 4.19% fitness gain and claims of superior detail preservation rest entirely on the unverified assumption that higher CHILL@UK and RPI_AXIS scores indicate better fidelity.

    Authors: We designed our framework specifically for no-reference scenarios, which are common in clinical CBCT where ground-truth reconstructions are often unavailable. The CHILL@UK and RPI_AXIS metrics are established no-reference quality assessment tools in the literature for medical images, and our qualitative visual comparisons corroborate the quantitative improvements in preserving fine details. We will revise the manuscript to include additional discussion on the reliability of these metrics based on existing validation studies and to explicitly state the limitation of not having ground-truth comparisons. This addresses the concern without altering the core no-reference contribution. revision: partial

  2. Referee: [Method description and results comparison] The paper does not provide an ablation study isolating the contribution of each proposed CSA modification (set-dependent local search, search-space-aware global search, objective-driven balance) or the chaotic initialization scheme. It is therefore unclear which components drive the observed improvements versus the baseline CSA, undermining the claim that the full set of modifications is necessary for the reported gains.

    Authors: We agree that an ablation study would provide clearer insight into the individual contributions of our proposed modifications. In the revised version of the manuscript, we will add an ablation study that evaluates the performance when each component (set-dependent local search, search-space-aware global search, objective-driven balance, and chaotic diagonal linear uniform initialization) is added incrementally to the standard CSA. This will demonstrate the necessity of the full set of modifications for achieving the reported gains. revision: yes

Circularity Check

0 steps flagged

No significant circularity in optimization framework or algorithm modifications

full rationale

The paper's core contribution is an empirical optimization procedure that tunes iterative reconstruction hyperparameters by directly maximizing two external no-reference metrics (CHILL@UK and RPI_AXIS) as fitness functions. The claimed algorithmic enhancements (set-dependent local search, search-space-aware global search, chaotic diagonal linear uniform initialization) are presented as additive mechanisms rather than redefinitions of the objective or the metrics themselves. Reported gains (4.19% average fitness, specific improvements on the two metrics) are the direct, expected output of any successful optimizer operating on those same fitness functions; they do not constitute a 'prediction' that reduces to the input by construction. No load-bearing self-citation, uniqueness theorem imported from prior author work, or ansatz smuggled via citation appears in the abstract or described framework. The derivation chain is therefore self-contained against external benchmarks and receives the default non-circularity finding.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only review prevents exhaustive extraction; the framework implicitly relies on standard metaheuristic assumptions such as the existence of an optimum in the parameter space and the validity of the chosen fitness metrics as surrogates for image quality.

axioms (1)
  • domain assumption Metaheuristic search algorithms can locate near-optimal parameter sets for iterative reconstruction when guided by no-reference quality metrics
    Central to the claim that the modified CSA produces superior results without reference data

pith-pipeline@v0.9.0 · 5642 in / 1263 out tokens · 45534 ms · 2026-05-10T18:40:35.287850+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

65 extracted references · 65 canonical work pages

  1. [1]

    Birkfellner, Applied Medical Image Processing: A Basic Course, CRC Press, 2024

    W. Birkfellner, Applied Medical Image Processing: A Basic Course, CRC Press, 2024

    work page 2024

  2. [2]

    W. A. Kalender, Computed tomography: fundamentals, system tech- nology, image quality, applications, John Wiley & Sons, 2011

    work page 2011

  3. [3]

    Walter, J

    C. Walter, J. C. Schmidt, K. Dula, A. Sculean, Cone beam computed tomography (cbct) for diagnosis and treatment planning in periodontol- ogy: A systematic review, Quintessence Int 47 (2016) 25–37. 37

    work page 2016

  4. [4]

    R. J. Hodges, K. A. Atchison, S. C. White, Impact of cone-beam computed tomography on orthodontic diagnosis and treatment plan- ning, American Journal of Orthodontics and Dentofacial Orthopedics 143 (2013) 665–674

    work page 2013

  5. [5]

    S. R. S. Islam, A. Biguri, C. Landi, G. Di Domenico, B. Schnei- der, P. Grün, C. Sarti, R. Woitek, A. Delmiglio, C.-B. Schönlieb, et al., Source-detector trajectory optimization for fov extension in den- tal cbct imaging, Computational and Structural Biotechnology Journal 24 (2024) 679–689

    work page 2024

  6. [6]

    Y. Song, W. Zhang, T. Wu, Y. Luo, J. Shi, X. Yang, Z. Deng, X. Qi, G. Li, S. Bai, et al., Ultra-sparse-view cone-beam ct reconstruction based strictly-structure-preserved deep neural network in image-guided radiation therapy, IEEE Transactions on Medical Imaging (2025)

    work page 2025

  7. [7]

    J. Zhou, A. Gopal, B. Zhang, H. Xu, S. Chen, B. Yi, G. Lasio, A novel optimization of cone beam ct frequency for lung radiation therapy based on an image-guided radiation therapy protocol and patient classification method, Translational Lung Cancer Research 14 (2025) 81

    work page 2025

  8. [8]

    Hatamikia, A

    S. Hatamikia, A. Biguri, G. Kronreif, M. Figl, T. Russ, J. Kettenbach, M. Buschmann, W. Birkfellner, Toward on-the-fly trajectory optimiza- tion for c-arm cbct under strong kinematic constraints, Plos one 16 (2021) e0245508

    work page 2021

  9. [9]

    E. Raz, E. Nossek, D. H. Sahlein, V. Sharashidze, V. Narayan, A. Ali, R. Esparza, S. Peschillo, C. Chung, F. Diana, et al., Principles, tech- niques and applications of high resolution cone beam ct angiography in the neuroangio suite, Journal of neurointerventional surgery 15 (2023) 600–607

    work page 2023

  10. [10]

    L. A. Feldkamp, L. C. Davis, J. W. Kress, Practical cone-beam algo- rithm, Journal of the Optical Society of America A 1 (1984) 612–619

    work page 1984

  11. [11]

    Hatamikia, A

    S. Hatamikia, A. Biguri, G. Kronreif, J. Kettenbach, T. Russ, H. Fur- tado, L. K. Shiyam Sundar, M. Buschmann, E. Unger, M. Figl, et al., Optimization for customized trajectories in cone beam computed tomog- raphy, Medical physics 47 (2020) 4786–4799. 38

    work page 2020

  12. [12]

    Coşkun Albayrak, Ö

    S. Coşkun Albayrak, Ö. S. Özdemir, Awareness of cone beam com- puted tomography (cbct) use and radiation safety among dentists and specialists, BMC Oral Health 25 (2025) 1436

    work page 2025

  13. [13]

    Bawazeer, K

    O. Bawazeer, K. Almutairi, H. Almutairi, M. Abuzaid, A. Ajlouni, S. Al- Qahtani, M. Qutub, M. Algethami, A. Alomari, Advancing radiation safety in dental cbct scans: Assessing the efficacy of barium sulfate shields in protecting the thyroid and eyes, Journal of Radiation Research and Applied Sciences 18 (2025) 101474

    work page 2025

  14. [14]

    Stiller, Basics of iterative reconstruction methods in computed to- mography: a vendor-independent overview, European journal of radiol- ogy 109 (2018) 147–154

    W. Stiller, Basics of iterative reconstruction methods in computed to- mography: a vendor-independent overview, European journal of radiol- ogy 109 (2018) 147–154

    work page 2018

  15. [15]

    M. J. Willemink, P. A. De Jong, T. Leiner, L. M. De Heer, R. A. Nievel- stein, R. P. Budde, A. M. Schilham, Iterative reconstruction techniques for computed tomography part 1: technical principles, European radi- ology 23 (2013) 1623–1631

    work page 2013

  16. [16]

    Biguri, M

    A. Biguri, M. Dosanjh, S. Hancock, M. Soleimani, Tigre: a matlab-gpu toolbox for cbct image reconstruction, Biomedical Physics & Engineer- ing Express 2 (2016) 055010

    work page 2016

  17. [17]

    P. C. Hansen, J. S. Jørgensen, Air tools ii: algebraic iterative recon- struction methods, improved implementation, Numerical Algorithms 79 (2018) 107–137

    work page 2018

  18. [18]

    Lohvithee, A

    M. Lohvithee, A. Biguri, M. Soleimani, Parameter selection in limited data cone-beam ct reconstruction using edge-preserving total variation algorithms, Physics in Medicine & Biology 62 (2017) 9295

    work page 2017

  19. [19]

    J. Duan, J. Cai, X. Mou, Region-based automatic regularization pa- rameter tuning in ct reconstruction, in: Proceedings of the Third Inter- national Symposium on Image Computing and Digital Medicine, 2019, pp. 55–58

    work page 2019

  20. [20]

    Zheng, E

    Z. Zheng, E. Papenhausen, K. Mueller, Dqs advisor: a visual inter- face and knowledge-based system to balance dose, quality, and recon- struction speed in iterative ct reconstruction with application to nlm- regularization, Physics in Medicine & Biology 58 (2013) 7857. 39

    work page 2013

  21. [21]

    J. Xu, F. Noo, Patient-specific hyperparameter learning for optimization-based ct image reconstruction, Physics in Medicine & Bi- ology 66 (2021) 19NT01

    work page 2021

  22. [22]

    C. Shen, Y. Gonzalez, L. Chen, S. B. Jiang, X. Jia, Intelligent parameter tuning in optimization-based iterative ct reconstruction via deep rein- forcement learning, IEEE transactions on medical imaging 37 (2018) 1430–1439

    work page 2018

  23. [23]

    Shen, M.-Y

    C. Shen, M.-Y. Tsai, Y. Gonzalez, L. Chen, S. B. Jiang, X. Jia, Quality- guided deep reinforcement learning for parameter tuning in iterative ct reconstruction, in: 15th International Meeting on Fully Three- Dimensional Image Reconstruction in Radiology and Nuclear Medicine, volume 11072, SPIE, 2019, pp. 6–10

    work page 2019

  24. [24]

    E. Y. Sidky, X. Pan, Image reconstruction in circular cone-beam com- puted tomography by constrained, total-variation minimization, Physics in Medicine & Biology 53 (2008) 4777

    work page 2008

  25. [25]

    W. Xu, K. Mueller, Using gpus to learn effective parameter settings for gpu-accelerated iterative ct reconstruction algorithms, in: GPU Com- puting Gems Emerald Edition, Elsevier, 2011, pp. 693–708

    work page 2011

  26. [26]

    Lohvithee, W

    M. Lohvithee, W. Sun, S. Chretien, M. Soleimani, Ant colony-based hyperparameter optimisation in total variation reconstruction in x-ray computed tomography, Sensors 21 (2021) 591

    work page 2021

  27. [27]

    A. K. Kar, Bio inspired computing–a review of algorithms and scope of applications, Expert Systems with Applications 59 (2016) 20–32

    work page 2016

  28. [28]

    Rajwar, K

    K. Rajwar, K. Deep, S. Das, An exhaustive review of the metaheuristic algorithms for search and optimization: taxonomy, applications, and open challenges, Artificial Intelligence Review 56 (2023) 13187–13257

    work page 2023

  29. [29]

    Askarzadeh, A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm, Computers & structures 169 (2016) 1–12

    A. Askarzadeh, A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm, Computers & structures 169 (2016) 1–12

    work page 2016

  30. [30]

    F. Xu, W. Xu, M. Jones, B. Keszthelyi, J. Sedat, D. Agard, K. Mueller, On the efficiency of iterative ordered subset reconstruction algo- rithms for acceleration on gpus, Computer methods and programs in biomedicine 98 (2010) 261–270. 40

    work page 2010

  31. [31]

    K. Deb, S. Agrawal, A. Pratap, T. Meyarivan, A fast elitist non- dominated sorting genetic algorithm for multi-objective optimization: Nsga-ii, in: International conference on parallel problem solving from nature, Springer, 2000, pp. 849–858

    work page 2000

  32. [32]

    Zheng, E

    Z. Zheng, E. Papenhausen, K. Mueller, Searching effective parameters for low-dose ct reconstruction by ant colony optimization, in: Int. Conf. Image Formation in X-Ray Computed Tomography, 2012, pp. 182–185

    work page 2012

  33. [33]

    Dorigo, M

    M. Dorigo, M. Birattari, T. Stutzle, Ant colony optimization, IEEE computational intelligence magazine 1 (2007) 28–39

    work page 2007

  34. [34]

    L. Liu, W. Lin, M. Jin, Reconstruction of sparse-view x-ray computed tomography using adaptive iterative algorithms, Computers in biology and medicine 56 (2015) 97–106

    work page 2015

  35. [35]

    S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein, et al., Dis- tributed optimization and statistical learning via the alternating di- rection method of multipliers, Foundations and Trends®in Machine learning 3 (2011) 1–122

    work page 2011

  36. [36]

    Dorigo, C

    M. Dorigo, C. Blum, Ant colony optimization theory: A survey, Theo- retical computer science 344 (2005) 243–278

    work page 2005

  37. [37]

    G.-H. Chen, J. Tang, S. Leng, Prior image constrained compressed sens- ing (piccs): a method to accurately reconstruct dynamic ct images from highly undersampled projection data sets, Medical physics 35 (2008) 660–663

    work page 2008

  38. [38]

    Hatamikia, A

    S. Hatamikia, A. Biguri, G. Kronreif, T. Russ, J. Kettenbach, W. Birk- fellner, Source-detector trajectory optimization for cbct metal artifact reduction based on piccs reconstruction, Zeitschrift für Medizinische Physik 34 (2024) 565–579

    work page 2024

  39. [39]

    G.-H. Chen, P. Thériault-Lauzier, J. Tang, B. Nett, S. Leng, J. Zam- belli, Z. Qi, N. Bevins, A. Raval, S. Reeder, et al., Time-resolved in- terventional cardiac c-arm cone-beam ct: An application of the piccs algorithm, IEEE transactions on medical imaging 31 (2011) 907–923. 41

    work page 2011

  40. [40]

    Hastings, S

    F. Hastings, S. Islam, M. S. Landman, S. Hatamikia, C.-B. Schönlieb, A. Biguri, Real-time cbct reconstructions using krylov solvers in re- peated scanning procedures, arXiv preprint arXiv:2509.08574 (2025)

    work page arXiv 2025

  41. [41]

    Samieiyan, P

    B. Samieiyan, P. MohammadiNasab, M. A. Mollaei, F. Hajizadeh, M. Kangavari, Solving dimension reduction problems for classification using promoted crow search algorithm (pcsa), Computing 104 (2022) 1255–1284

    work page 2022

  42. [42]

    A. M. Anter, M. Ali, Feature selection strategy based on hybrid crow search optimization algorithm integrated with chaos theory and fuzzy c-means algorithm for medical diagnosis problems, Soft Computing 24 (2020) 1565–1584

    work page 2020

  43. [43]

    Lenin Fred, S

    A. Lenin Fred, S. Kumar, P. Padmanaban, B. Gulyas, H. Ajay Kumar, Fuzzy-crow search optimization for medical image segmentation, in: Applications of hybrid metaheuristic algorithms for image processing, Springer, 2020, pp. 413–439

    work page 2020

  44. [44]

    J. O. Agushaka, A. E. Ezugwu, Initialisation approaches for population- based metaheuristic algorithms: a comprehensive review, Applied Sci- ences 12 (2022) 896

    work page 2022

  45. [45]

    Tharwat, W

    A. Tharwat, W. Schenck, Population initialization techniques for evo- lutionary algorithms for single-objective constrained optimization prob- lems: Deterministic vs. stochastic techniques, Swarm and Evolutionary Computation 67 (2021) 100952

    work page 2021

  46. [46]

    M. D. McKay, R. J. Beckman, W. J. Conover, A comparison of three methods for selecting values of input variables in the analysis of output from a computer code, Technometrics 42 (2000) 55–61

    work page 2000

  47. [47]

    Q. Li, Y. Bai, W. Gao, Improved initialization method for metaheuristic algorithms: A novel search space view, Ieee Access 9 (2021) 121366– 121384

    work page 2021

  48. [48]

    W. Lee, F. Wagner, A. Galdran, Y. Shi, W. Xia, G. Wang, X. Mou, M. A. Ahamed, A. A. Z. Imran, J. E. Oh, et al., Low-dose computed to- mography perceptual image quality assessment, Medical Image Analysis 99 (2025) 103343. 42

    work page 2025

  49. [49]

    Ouadfel, M

    S. Ouadfel, M. Abd Elaziz, Enhanced crow search algorithm for feature selection, Expert Systems with Applications 159 (2020) 113572

    work page 2020

  50. [50]

    G. I. Sayed, A. E. Hassanien, A. T. Azar, Feature selection via a novel chaotic crow search algorithm, Neural computing and applications 31 (2019) 171–188

    work page 2019

  51. [51]

    Samieiyan, P

    B. Samieiyan, P. MohammadiNasab, M. A. Mollaei, F. Hajizadeh, M. Kangavari, Novel optimized crow search algorithm for feature se- lection, Expert Systems with Applications 204 (2022) 117486

    work page 2022

  52. [52]

    S. B. Coban, Sophiabeads datasets project documentation and tutorials, MIMS Eprints (2015)

    work page 2015

  53. [53]

    A. H. Andersen, A. C. Kak, Simultaneous algebraic reconstruction tech- nique (sart): a superior implementation of the art algorithm, Ultrasonic imaging 6 (1984) 81–94

    work page 1984

  54. [54]

    Keuschnigg, D

    P. Keuschnigg, D. Kellner, K. Fritscher, A. Zechner, U. Mayer, P. Huber, F. Sedlmayer, H. Deutschmann, P. Steininger, Nine-degrees-of-freedom flexmap for a cone-beam computed tomography imaging device with independently movable source and detector, Medical physics 44 (2017) 132–142

    work page 2017

  55. [55]

    Hatamikia, G

    S. Hatamikia, G. Oberoi, E. Unger, G. Kronreif, J. Kettenbach, M. Buschmann, M. Figl, B. Knäusl, F. Moscato, W. Birkfellner, Addi- tively manufactured patient-specific anthropomorphic thorax phantom with realistic radiation attenuation properties, Frontiers in Bioengineer- ing and Biotechnology 8 (2020) 385

    work page 2020

  56. [56]

    Biguri, T

    A. Biguri, T. Sadakane, R. Lindroos, Y. Liu, M. S. Landman, Y. Du, M. Lohvithee, S. Kaser, S. Hatamikia, R. Bryll, et al., Tigre v3: Efficient and easy to use iterative computed tomographic reconstruction toolbox for real datasets, Engineering Research Express 7 (2025) 015011

    work page 2025

  57. [57]

    F. Zarb, L. Rainford, M. F. McEntee, Image quality assessment tools for optimization of ct images, Radiography 16 (2010) 147–153

    work page 2010

  58. [58]

    Breger, C

    A. Breger, C. Karner, I. Selby, J. Gröhl, S. Dittmer, E. Lilley, J. Babar, J. Beckford, T. R. Else, T. J. Sadler, et al., A study on the adequacy of common iqa measures for medical images, in: International Conference 43 on Medical Imaging and Computer-Aided Diagnosis, Springer, 2024, pp. 451–462

    work page 2024

  59. [59]

    Zhang, L

    L. Zhang, L. Zhang, X. Mou, D. Zhang, Fsim: A feature similarity index for image quality assessment, IEEE transactions on Image Processing 20 (2011) 2378–2386

    work page 2011

  60. [60]

    Karner, J

    C. Karner, J. Gröhl, I. Selby, J. Babar, J. Beckford, T. R. Else, T. J. Sadler, S. Shahipasand, A. Thavakumar, M. Roberts, et al., Parameter choices in haarpsi for iqa with medical images, in: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), IEEE, 2025, pp. 1–5

    work page 2025

  61. [61]

    Zhang, Y

    L. Zhang, Y. Shen, H. Li, Vsi: A visual saliency-induced index for perceptual image quality assessment, IEEE Transactions on Image pro- cessing 23 (2014) 4270–4281

    work page 2014

  62. [62]

    H. R. Sheikh, A. C. Bovik, Image information and visual quality, IEEE Transactions on image processing 15 (2006) 430–444

    work page 2006

  63. [63]

    K. Ding, K. Ma, S. Wang, E. P. Simoncelli, Image quality assessment: Unifying structure and texture similarity, IEEE transactions on pattern analysis and machine intelligence 44 (2020) 2567–2581

    work page 2020

  64. [64]

    Zhang, P

    R. Zhang, P. Isola, A. A. Efros, E. Shechtman, O. Wang, The unreason- able effectiveness of deep features as a perceptual metric, in: Proceed- ings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 586–595

    work page 2018

  65. [65]

    Breger, A

    A. Breger, A. Biguri, M. S. Landman, I. Selby, N. Amberg, E. Brunner, J. Gröhl, S. Hatamikia, C. Karner, L. Ning, et al., A study of why we need to reassess full reference image quality assessment with medical images, Journal of Imaging Informatics in Medicine 38 (2025) 3444– 3469. 44 Appendix A. Results correlation analysis According to the results of ta...

    work page 2025