arXiv subjects

Konrad Klimaszewski

Publications and source records attributed to Konrad Klimaszewski.

16 recordsLinked to original sources

arXiv2026

A systematic evaluation of machine learning classifiers for event-by-event background rejection in LAFOV PET scanners

The introduction of LAFOV PET scanners brings significant sensitivity gains but also a substantial increase in the background rate from accidental coincidences, phantom-scattered and detector-scattered photons. While machine learning methods have been applied to background reduction in PET imaging, they target specific background components in post-processing rather than event-by-event classification on the raw data. In this work, we formulate coincidence classification as a supervised multi-class problem and evaluate XGBoost, AdaBoost and Neural Network classifiers as pre-reconstruction filters, using Monte Carlo simulations of the Siemens Biograph Vision Quadra scanner with NEMA IEC and anthropomorphic XCAT phantoms. We investigate two feature sets: a 4-feature representation based on the Attenuation Factor, photon time difference, energy sum, and energy difference, and an extended 6-feature set that incorporates topology-based variables. A systematic robustness study via cross-phantom inference reveals that the 4-feature models generalise significantly better across different phantom geometries, with XGBoost suffering an accuracy loss of only 0.04 compared to 0.13 for the 6-feature variant. Our best models achieve accuracies of up to 0.74 and 0.69 for the NEMA IEC and XCAT phantoms, respectively, outperforming traditional geometry-based cuts. However, we show that this compact feature set not only provides limited suppression of in-phantom scattered coincidences, but it also can lead to non-trivial spatial patterns. With scattered coincidences being the dominant background component in clinical conditions, this suggests that while the method serves as an effective and geometry-agnostic replacement for traditional cut-based selection, meaningful further gains in image quality will require either larger input representations or dedicated treatment of the phantom-scattered component.

cs.CV↗

arXiv2026

CAD-to-CT Registration of Cylindrical Objects via Ellipse-Based Axis Estimation

Accurate registration of CAD models to CT scans is essential for establishing ground truth geometry in volumetric imaging. Obtaining reliable object masks is of growing importance in machine learning settings; as recent architectures grow more capable, huge datasets are required to fully utilise their capabilities. Traditional intensity-based methods fail when CT grayscale values lack calibration references, while point-based algorithms (e.g., ICP, RANSAC) require feature correspondence unavailable between idealized CAD geometry and noisy volumetric CT data. We propose a two-stage geometric registration method for cylindrical objects (ionization chambers) that takes advantage of the distinctive geometric features of the objects. First, we estimate the 3D rotation axis by detecting elliptical cross-sections across CT slices, fitting ellipses to edge-detected contours, and performing PCA on the fitted ellipse centers after RANSAC outlier removal. Second, we voxelize the CAD model, orient it along the detected axis, and maximize volumetric overlap with the CT scan through translational adjustment. This approach achieves robust registration with tilt and orientation errors below $0.1^\circ$ without intensity calibration or feature matching. Once registered, the aligned CAD model provides ground truth geometry for applications including machine learning-based object localization and automated analysis in industrial CT workflows.

cs.CV↗

arXiv2026

A Monte Carlo positronium decay source model with multiple annihilation channels in GATE

Positronium-based imaging requires realistic modelling of positronium (Ps) decay in matter. We introduce a modular Ps decay model implemented in GATE 9.4 and GATE 10, enabling the definition of an arbitrary number of decay channels characterised by lifetime, branching fraction, annihilation multiplicity (2g/3g), and optional prompt photon emission. The model is validated through analytical and numerical benchmarks, including lifetime distributions, branching fraction consistency, photon kinematics, and prompt photon emission. Its practical applicability is demonstrated using simulations of mixed annihilation scenarios and the NEMA IEC phantom with a large field-of-view PET system. The proposed model accurately reproduces input lifetime distributions as weighted sums of exponential components and correctly samples decay channel fractions. Simulated two- and three-photon annihilation kinematics are consistent with theoretical expectations. Complex mixtures of decay channels, including varying 3g-to-2g ratios and multi-component ortho-positronium lifetimes, are correctly modelled, with observable signatures reflected in both temporal and energy distributions. Phantom simulations demonstrate the capability to generate realistic positronium-sensitive datasets. This work provides the first general-purpose, multi-channel positronium decay model integrated into GATE, enabling realistic simulations of positronium behaviour in complex media. The model supports the development and optimisation of positronium-based imaging techniques, including PLI and multi-photon PET, and applies to medical imaging, industrial tomography, and fundamental physics studies. Its public availability and compatibility with standard GATE workflows make it a valuable tool for the broader research community.

physics.med-ph↗

arXiv2026

DSS-GAN: Directional State Space GAN with Mamba backbone for Class-Conditional Image Synthesis

We present DSS-GAN, the first generative adversarial network to employ Mamba as a hierarchical generator backbone for noise-to-image synthesis. The central contribution is Directional Latent Routing (DLR), a novel conditioning mechanism that decomposes the latent vector into direction-specific subvectors, each jointly projected with a class embedding to produce a feature-wise affine modulation of the corresponding Mamba scan. Unlike conventional class conditioning that injects a global signal, DLR couples class identity and latent structure along distinct spatial axes of the feature map, applied consistently across all generative scales. DSS-GAN achieves improved FID, KID, and precision-recall scores compared to StyleGAN2-ADA across multiple tested datasets. Analysis of the latent space reveals that directional subvectors exhibit measurable specialization: perturbations along individual components produce structured, direction-correlated changes in the synthesized image.

cs.LG↗

arXiv2025

Improving PET scanner time-of-flight resolution using additional prompt photon

Positronium Imaging requires two classes of events: double-coincidences originated from pair of back-to-back annihilation photons and triple-coincidences comprised with two annihilation photons and one additional prompt photon. The standard reconstruction of the emission position along the line-of-response of triple-coincidence event is the same as in the case of double-coincidence event; an information introduced by the high-energetic prompt photon is ignored. In this study, we propose to extend the reconstruction of position of triple-coincidence event by taking into account the time and position of prompt photon. We incorporate the knowledge about the positronium lifetime distribution and discuss the limitations of the method based on the simulation data. We highlight that the uncertainty of the estimate provided by prompt photon alone is much higher than the standard deviation estimated based on two annihilation photons. We finally demonstrate the extent of resolution improvement that can be obtained when estimated using three photons.

physics.med-ph↗

arXiv2024

Preliminary study on artificial intelligence methods for cybersecurity threat detection in computer networks based on raw data packets

Most of the intrusion detection methods in computer networks are based on traffic flow characteristics. However, this approach may not fully exploit the potential of deep learning algorithms to directly extract features and patterns from raw packets. Moreover, it impedes real-time monitoring due to the necessity of waiting for the processing pipeline to complete and introduces dependencies on additional software components. In this paper, we investigate deep learning methodologies capable of detecting attacks in real-time directly from raw packet data within network traffic. We propose a novel approach where packets are stacked into windows and separately recognised, with a 2D image representation suitable for processing with computer vision models. Our investigation utilizes the CIC IDS-2017 dataset, which includes both benign traffic and prevalent real-world attacks, providing a comprehensive foundation for our research.

cs.CV↗

arXiv2024

Performance of GAN-based augmentation for deep learning COVID-19 image classification

The biggest challenge in the application of deep learning to the medical domain is the availability of training data. Data augmentation is a typical methodology used in machine learning when confronted with a limited data set. In a classical approach image transformations i.e. rotations, cropping and brightness changes are used. In this work, a StyleGAN2-ADA model of Generative Adversarial Networks is trained on the limited COVID-19 chest X-ray image set. After assessing the quality of generated images they are used to increase the training data set improving its balance between classes. We consider the multi-class classification problem of chest X-ray images including the COVID-19 positive class that hasn't been yet thoroughly explored in the literature. Results of transfer learning-based classification of COVID-19 chest X-ray images are presented. The performance of several deep convolutional neural network models is compared. The impact on the detection performance of classical image augmentations i.e. rotations, cropping, and brightness changes are studied. Furthermore, classical image augmentation is compared with GAN-based augmentation. The most accurate model is an EfficientNet-B0 with an accuracy of 90.2 percent, trained on a dataset with a simple class balancing. The GAN augmentation approach is found to be subpar to classical methods for the considered dataset.

eess.IV↗

arXiv2024

Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification

The availability of training data is one of the main limitations in deep learning applications for medical imaging. Data augmentation is a popular approach to overcome this problem. A new approach is a Machine Learning based augmentation, in particular usage of Generative Adversarial Networks (GAN). In this case, GANs generate images similar to the original dataset so that the overall training data amount is bigger, which leads to better performance of trained networks. A GAN model consists of two networks, a generator and a discriminator interconnected in a feedback loop which creates a competitive environment. This work is a continuation of the previous research where we trained StyleGAN2-ADA by Nvidia on the limited COVID-19 chest X-ray image dataset. In this paper, we study the dependence of the GAN-based augmentation performance on dataset size with a focus on small samples. Two datasets are considered, one with 1000 images per class (4000 images in total) and the second with 500 images per class (2000 images in total). We train StyleGAN2-ADA with both sets and then, after validating the quality of generated images, we use trained GANs as one of the augmentations approaches in multi-class classification problems. We compare the quality of the GAN-based augmentation approach to two different approaches (classical augmentation and no augmentation at all) by employing transfer learning-based classification of COVID-19 chest X-ray images. The results are quantified using different classification quality metrics and compared to the results from the literature. The GAN-based augmentation approach is found to be comparable with classical augmentation in the case of medium and large datasets but underperforms in the case of smaller datasets. The correlation between the size of the original dataset and the quality of classification is visible independently from the augmentation approach.

eess.IV↗

arXiv2024

Discrete symmetries tested at 10$^{-4}$ precision using linear polarization of photons from positronium annihilations

Discrete symmetries play an important role in particle physics with violation of CP connected to the matter-antimatter imbalance in the Universe. We report the most precise test of P, T and CP invariance in decays of ortho-positronium, performed with methodology involving polarization of photons from these decays. Positronium, the simplest bound state of an electron and positron, is of recent interest with discrepancies reported between measured hyperfine energy structure and theory at the level of $10^{-4}$ signaling a need for better understanding of the positronium system at this level. We test discrete symmetries using photon polarizations determined via Compton scattering in the dedicated J-PET tomograph on an event-by-event basis and without the need to control the spin of the positronium with an external magnetic field, in contrast to previous experiments. Our result is consistent with QED expectations at the level of 0.0007 and one standard deviation.

hep-ph↗

arXiv2023

Comparative studies of the sensitivities of sparse and full geometries of Total-Body PET scanners built from crystals and plastic scintillators

Background: Total-Body imaging offers high sensitivity, single-bed position, and low dose, but high construction costs limit worldwide utilization. This study compares existing and developing tomographs using plastic scintillators via simulations to propose a cost-efficient Total-Body PET scanner. Methods: Simulations of eight uEXPLORER tomographs with different scintillator materials, axial field-of-view, and detector configuration, and eight J-PET scanners with various field-of-view, plastic scintillator cross-sections, and layers were performed. Biograph Vision was also simulated. Two types of simulations were conducted with a central source and a water-filled phantom. Results: BGO crystal-based scanners showed the best sensitivity (350 cps/kBq at the center). Sparse geometry or LYSO crystals reduced sensitivity. J-PET design showed similar sensitivity to sparse LYSO detectors, with full body coverage and additional gain for brain imaging. Conclusion: The J-PET tomography system using plastic scintillators could be a cost-efficient alternative for Total-Body PET scanners, overcoming high construction costs while maintaining sensitivity

physics.med-ph↗

arXiv2023

Feasibility of the J-PET to monitor range of therapeutic proton beams

Objective: The aim of this work is to investigate the feasibility of the Jagiellonian Positron Emission Tomography (J-PET) scanner for intra-treatment proton beam range monitoring. Approach: The Monte Carlo simulation studies with GATE and PET image reconstruction with CASToR were performed in order to compare six J-PET scanner geometries (three dual-heads and three cylindrical). We simulated proton irradiation of a PMMA phantom with a Single Pencil Beam (SPB) and Spread-Out Bragg Peak (SOBP) of various ranges. The sensitivity and precision of each scanner were calculated, and considering the setup's cost-effectiveness, we indicated potentially optimal geometries for the J-PET scanner prototype dedicated to the proton beam range assessment. Main results: The investigations indicate that the double-layer cylindrical and triple-layer double-head configurations are the most promising for clinical application. We found that the scanner sensitivity is of the order of 10$^{-5}$ coincidences per primary proton, while the precision of the range assessment for both SPB and SOBP irradiation plans was found below 1 mm. Among the scanners with the same number of detector modules, the best results are found for the triple-layer dual-head geometry. Significance: We performed simulation studies demonstrating that the feasibility of the J-PET detector for PET-based proton beam therapy range monitoring is possible with reasonable sensitivity and precision enabling its pre-clinical tests in the clinical proton therapy environment. Considering the sensitivity, precision and cost-effectiveness, the double-layer cylindrical and triple-layer dual-head J-PET geometry configurations seem promising for the future clinical application. Experimental tests are needed to confirm these findings.

physics.med-ph↗

arXiv2022

Realistic Total-Body J-PET Geometry Optimization -- Monte Carlo Study

Total-Body PET is one of the most promising medical diagnostics modalities. The high sensitivity provided by Total-Body technology can be advantageous for novel tomography methods like positronium imaging. Several efforts are ongoing to lower the price of the TB-PET systems. Among the alternatives, the Jagiellonian PET (J-PET) technology, based on plastic scintillator strips, offers a low-cost alternative. The work aimed to compare five Total-Body J-PET geometries as a possible next generation J-PET scanner design. We present comparative studies of performance characteristics of the cost-effective Total-Body PET scanners using J-PET technology. We investigated in silico five Total-Body scanner geometries. Monte Carlo simulations of the XCAT phantom, the 2-meter sensitivity line source and positronium sensitivity phantoms were performed. We compared the sensitivity profiles for 2-gamma and 3-gamma tomography, relative cost of the setups and performed quantitative analysis of the reconstructed images. The analysis of the reconstructed XCAT images reveals the superiority of the seven-ring scanners over the three-ring setups. However, the three-ring scanners would be approximately 2-3 times cheaper. The peak sensitivity values for two-gamma vary from 20 to 34 cps/kBq. The sensitivity curves for the positronium tomography have a similar shape to the two-gamma sensitivity profiles. The peak values are lower compared to the two-gamma cases, from about 20-28 times, with a maximum of 1.66 cps/kBq. The results show the feasibility of multi-organ imaging of all the systems to be considered for the next generation of TB J-PET designs. The relative cost for all the scanners is about 10-4 times lower compared to the cost of the uExplorer. These properties coupled together with J-PET cost-effectiveness, make the J-PET technology an attractive solution for broad application in clinics.

physics.med-ph↗

arXiv2021

Positronium imaging with the novel multiphoton PET scanner

In vivo assessment of cancer and precise location of altered tissues at initial stages of molecular disorders are important diagnostic challenges. Positronium is copiously formed in the free molecular spaces in the patient's body during positron emission tomography (PET). The positronium properties vary according to the size of inter- and intramolecular voids and the concentration of molecules in them such as, e.g., molecular oxygen, O2; therefore, positronium imaging may provide information about disease progression during the initial stages of molecular alterations. Current PET systems do not allow acquisition of positronium images. This study presents a new method that enables positronium imaging by simultaneous registration of annihilation photons and deexcitation photons from pharmaceuticals labeled with radionuclides. The first positronium imaging of a phantom built from cardiac myxoma and adipose tissue is demonstrated. It is anticipated that positronium imaging will substantially enhance the specificity of PET diagnostics.

physics.med-ph↗

arXiv2021

Testing CPT symmetry in ortho-positronium decays with positronium annihilation tomography

Charged lepton system symmetry under combined charge, parity, and time-reversal transformation (CPT) remains scarcely tested. Despite stringent quantum-electrodynamic limits, discrepancies in predictions for the electron-positron bound state (positronium atom) motivate further investigation, including fundamental symmetry tests. While CPT noninvariance effects could be manifested in non-vanishing angular correlations between final-state photons and spin of annihilating positronium, measurements were previously limited by knowledge of the latter. Here, we demonstrate tomographic reconstruction techniques applied to three-photon annihilations of ortho-positronium atoms to estimate their spin polarisation without magnetic field or polarised positronium source. We use a plastic-scintillator-based positron-emission-tomography scanner to record ortho-positronium (o-Ps) annihilations with single-event estimation of o-Ps spin and determine the complete spectrum of an angular correlation operator sensitive to CPT-violating effects. We find no violation at the precision level of 10^{-4}, with an over threefold improvement on the previous measurement.

nucl-ex↗

arXiv2021

Simulating NEMA characteristics of the modular total-body J-PET scanner -- an economic total-body PET from plastic scintillators

The purpose of the presented research is estimation of the performance characteristics of the economic Total-Body Jagiellonian-PET system (TB-J-PET) constructed from plastic scintillators. The characteristics are estimated according to the NEMA NU-2-2018 standards utilizing the GATE package. The simulated detector consists of 24 modules, each built out of 32 plastic scintillator strips (each with cross section of 6 mm times 30 mm and length of 140 cm or 200 cm) arranged in two layers in regular 24-sided polygon circumscribing a circle with the diameter of 78.6 cm. For the TB-J-PET with an axial field-of-view (AFOV) of 200 cm, a spatial resolutions of 3.7 mm (transversal) and 4.9 mm (axial) are achieved. The NECR peak of 630 kcps is expected at 30 kBq/cc activity concentration and the sensitivity at the center amounts to 38 cps/kBq. The SF is estimated to 36.2 %. The values of SF and spatial resolution are comparable to those obtained for the state-of-the-art clinical PET scanners and the first total-body tomographs: uExplorer and PennPET. With respect to the standard PET systems with AFOV in the range from 16 cm to 26 cm, the TB-J-PET is characterized by an increase in NECR approximately by factor of 4 and by the increase of the whole-body sensitivity by factor of 12.6 to 38. The TOF resolution for the TB-J-PET is expected to be at the level of CRT=240 ps (FWHM). For the TB-J-PET with an axial field-of-view (AFOV) of 140 cm, an image quality of the reconstructed images of a NEMA IEC phantom was presented with a contrast recovery coefficient (CRC) and a background variability parameters. The increase of the whole-body sensitivity and NECR estimated for the TB-J-PET with respect to current commercial PET systems makes the TB-J-PET a promising cost-effective solution for the broad clinical applications of total-body PET scanners.

physics.ins-det↗

arXiv2018

Estimating the NEMA characteristics of the J-PET tomograph using the GATE package

The novel whole-body PET system based on plastic scintillators is developed by the {J-PET} Collaboration. It consists of plastic scintillator strips arranged axially in the form of a cylinder, allowing the cost-effective construction of the total-body PET. In order to determine properties of the scanner prototype and optimize its geometry, advanced computer simulations using the GATE software were performed. The spatial resolution, the sensitivity, the scatter fraction and the noise equivalent count rate were estimated according to the NEMA norm as a function of the length of the tomograph, number of the detection layers, diameter of the tomographic chamber and for various types of the applied readout. For the single-layer geometry with the diameter of 85 cm, strip length of 100 cm, cross-section of 4 mm x 20 mm and silicon photomultipliers with the additional layer of wavelength shifter as the readout, the spatial resolution (FWHM) in the centre of the scanner is equal to 3 mm (radial, tangential) and 6 mm (axial). For the analogous double-layer geometry with the same readout, diameter and scintillator length, with the strip cross-section of 7 mm x 20 mm, the NECR peak of 300 kcps was reached at 40 kBq/cc activity concentration, the scatter fraction is estimated to about 35% and the sensitivity at the centre amounts to 14.9 cps/kBq. Sensitivity profiles were also determined.

physics.ins-det↗