Investigating particle track topology for range telescopes in particle radiography using convolutional neural networks

Pettersen, Helge Egil Seime; Max, Aehle,; Alme, J.; Barnaföldi, G. G.; Borshchov, V. I.; Brink, A. van den; Chaar, Mamdouh; Eikeland, Viljar Nilsen; Феофилов, Г.; Garth, Christoph; Gauger, Nicolas R.; Genov, Georgi; Grøttvik, Ola Slettevoll; Helstrup, H.; Igolkin, S. N.; Kobdaj, C.; Kortus, Tobias; Leonhardt, Viktor; Mehendale, Shruti; Mulawade, Raju Ningappa; Odland, O.H.; Papp, Gábor; Peitzmann, T.; Piersimoni, Pierluigi; Protsenko, Maksym; Rehman, A.; Richter, Matthias; Santana, Joshua; Schilling, Alexander; Seco, Joao; Songmoolnak, A.; Sølie, Jarle Rambo; Tambave, Ganesh Jagannath; Tymchuk, I.; Ullaland, K.; Varga-Kőfaragó, M.; Volz, Lennart; Wagner, B.; Wendzel, Steffen; Wiebel, Alexander; Xiao, RenZheng; Yokoyama, H.; Zillien, Sebastian; Röhrich, D.

doi:10.1080/0284186x.2021.1949037

“…The remaining protons are label as good. Recently, authors have reported a ∼97% accuracy in this task using a CNN (Pettersen et al 2021). This method, however, is not entirely satisfactory for a multi-proton pCT system as sometimes the correctly reconstructed energy of two simultaneous protons is swapped due to matching errors between the position tracker and the energy tagger.…”

Section: Resultsmentioning

confidence: 99%

A novel range telescope concept for proton CT

Granado-González¹,

Jesús-Valls²,

Lux³

et al. 2022

View full text Add to dashboard Cite

Proton beam therapy can potentially offer improved treatment for cancers of the head and neck and in paediatric patients. There has been asharp uptake of proton beam therapy in recent years as improved delivery techniques and patient benefits are observed. However, treatments are currently planned using conventional x-ray CT images due to the absence of devices able to perform high quality proton computed tomography(pCT) under realistic clinical conditions. A new plastic-scintillator-based range telescope concept, named ASTRA, is proposed here to measure the proton’s energy loss in a pCT system. Simulations conducted using GEANT4 yield an expected energy resolution of 0.7%. If calorimetric information is used the energy resolution could be further improved to about 0.5%. In addition, the ability of ASTRA to track multiple protons simultaneously is presented. Due to its fast components, ASTRA is expected to reach unprecedented data collection rates, similar to 10^8 protons/s.The performance of ASTRA has also been tested by simulating the imaging of phantoms. The results show excellent image contrast and relative stopping power reconstruction.

show abstract

“…To remove those particle trajectories from evaluation, we apply a cut based filtering, limiting the scattering angle in calorimeter and tracking layers to ∆θ max = 271 mrad, corresponding to a 2σ upper bound for particles in the last layer before stopping using extrapolated values from the PSTAR database [57]. Further, all tracks are required to show the characteristic high energy deposition of a Bragg peak, which we identify by an energy filter in the last layer of ∆E min = 2.5 keV/µm [9], [58].…”

Section: Track Filteringmentioning

confidence: 99%

Towards Neural Charged Particle Tracking in Digital Tracking Calorimeters with Reinforcement Learning

Kortus¹,

Gauger²

2023

Preprint

0

View full text Add to dashboard Cite

<p>We propose a novel reconstruction scheme for reconstructing charged particles in digital tracking calorimeters using model-free reinforcement learning aiming to benefit from the rapid progress and success of neural network architectures for tracking without the dependency on simulated or manually labeled data. Here we optimize by trial-and-error a behavior policy acting as a heuristic approximation to the full combinatorial optimization problem, maximizing the physical plausibility of sampled trajectories. In modern data processing pipelines used in high energy physics experiments and related high energy physics driven applications tracking plays an essential role allowing to identify and follow charged particle trajectories traversing particle detectors. Due to the usual high multiplicity of charged particles as well as the occurring physical interactions, randomly deflecting the particles from their initial path, the reconstruction is a challenging undertaking, requiring fast, accurate and robust algorithms. Our approach works on graph-structured data, capturing possible track hypotheses through edge connections between particles in the sensitive detector layers. We demonstrate in a comprehensive study on simulated data generated for a particle detector used for proton computed tomography, the overall high potential as well as the competitiveness of our approach compared to a heuristic search algorithm and a model trained on ground truth information. Finally, we point out limitations of our approach, guiding towards a robust foundation for further development of reinforcement learning based tracking algorithms in high energy physics.</p>

show abstract

“…To remove those particle trajectories from evaluation, we apply a cut based filtering, limiting the scattering angle in calorimeter and tracking layers to ∆θ max = 271 mrad, corresponding to a 2σ upper bound for particles in the last layer before stopping using extrapolated values from the PSTAR database [55]. Further, all tracks are required to show the characteristic high energy deposition of a Bragg peak, which we identify by an energy filter in the last layer of ∆E min = 2.5 keV/µm [9], [56].…”

Section: Track Filteringmentioning

confidence: 99%

Towards Neural Charged Particle Tracking in Digital Tracking Calorimeters with Reinforcement Learning

Kortus¹,

Gauger²

2023

Preprint

Self Cite

0

View full text Add to dashboard Cite

<p>We propose a novel reconstruction scheme for reconstructing charged particles in digital tracking calorimeters using model-free reinforcement learning aiming to benefit from the rapid progress and success of neural network architectures for tracking without the dependency on simulated or manually labeled data. Here we optimize by trial-and-error a behavior policy acting as a heuristic approximation to the full combinatorial optimization problem, maximizing the physical plausibility of sampled trajectories. In modern data processing pipelines used in high energy physics experiments and related high energy physics driven applications tracking plays an essential role allowing to identify and follow charged particle trajectories traversing particle detectors. Due to the usual high multiplicity of charged particles as well as the occurring physical interactions, randomly deflecting the particles from their initial path, the reconstruction is a challenging undertaking, requiring fast, accurate and robust algorithms. Our approach works on graph-structured data, capturing possible track hypotheses through edge connections between particles in the sensitive detector layers. We demonstrate in a comprehensive study on simulated data generated for a particle detector used for proton computed tomography, the overall high potential as well as the competitiveness of our approach compared to a heuristic search algorithm and a model trained on ground truth information. Finally, we point out limitations of our approach, guiding towards a robust foundation for further development of reinforcement learning based tracking algorithms in high energy physics.</p>

show abstract

Investigating particle track topology for range telescopes in particle radiography using convolutional neural networks

Cited by 8 publications

References 29 publications

A novel range telescope concept for proton CT

A novel range telescope concept for proton CT

Towards Neural Charged Particle Tracking in Digital Tracking Calorimeters with Reinforcement Learning

Towards Neural Charged Particle Tracking in Digital Tracking Calorimeters with Reinforcement Learning

Contact Info

Product

Resources

About