PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Convolutional neural networks in the classification of multiphoton coincidences in a J-PET scanner

Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
This work describes an investigation into the utilization of convolutional neural networks for the classification of three-photon coincidences, focusing specifically on the para- -positronium decay associated with a photon from nuclear deexcitation. The data were simulated using the Monte Carlo method, with scandium-44 as the source of β+ decays. A preprocessing method that allowed for initial cleaning of the training data was described. Subsequently, the parameters of the method for transforming tabular data into images were optimized. Finally, the created images were used to train a binary classifier using a convolutional network model. The developed data preprocessing step and transformation method into image format enabled the achievement of a precision rate of 52% at a sensitivity level of 95%, which was a 10 percentage point improvement compared to the logistic regression model.
Rocznik
Strony
43--47
Opis fizyczny
Bibliogr. 17 poz., rys., tab.
Twórcy
  • Department of Complex Systems, National Centre for Nuclear Research, Otwock-Świerk, Poland
  • Department of Complex Systems, National Centre for Nuclear Research, Otwock-Świerk, Poland
  • Department of Complex Systems, National Centre for Nuclear Research, Otwock-Świerk, Poland
Bibliografia
  • 1. Badawi RD, Shi H, Hu P, Chen S, Xu T, Price PM, et al. First Human Imaging Studies with the EXPLORER Total-Body PET Scanner. J. Nucl. Med. 2018;60:299-303.
  • 2. Holy EN, Fan AP, Alfaro ER, Fletcher E, Spencer BA, Cherry SR, et al. Non-invasive quantification and SUVR validation of [18F]-florbetaben with total-body EXPLORER PET. Alzheimer’s Dement. 2022;18:e066123.
  • 3. Jean JY, Mallon PE, Schrader DM. Introduction to Positron and Positronium Chemistry. In: Jean JY, Mallon PE, Schrader DM, editors. Principles and applications of positron and positronium chemistry. Singapore: World Scientific Publishing Co Pte Ltd; 2003. p. 1-15.
  • 4. Moskal P. Positronium Imaging. In: 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). IEEE 2020; 2020; New York City. USA: 2020. p. 1-3.
  • 5. Moskal P, Dulski K, Chug N, Curceanu C, Czerwiński E, Dadgar M, et al.: Positronium imaging with the novel multiphoton PET scanner. Sci. Adv. 2021;7:eabh4394.
  • 6. Sharma A, Vans E, Shigemizu D, Boroevich KA, Tsunoda T. Deepinsight: A methodology to transform a non-image data to an image for convolution neural network architecture. Sci. Rep. 2019;9:11399.
  • 7. Konieczka P, Raczyński L, Wiślicki W, Fedoruk O, Klimaszewski K, Kopka P, et al.: Transformation of PET raw data into images for event classification using convolutional neural networks. Math. Biosci. Eng. 2023;20:14938-58.
  • 8. Moskal P, Niedźwiecki S, Bednarski T, Czerwiński E, Kapłon Ł, Kubicz E, et al. Test of a single module of the J-PET scanner based on plastic scintillators. Nucl. Instrum. Meth. Phys. Res. A. 2014;764:317-21.
  • 9. Raczyński L, Moskal P, Kowalski P, Wiślicki W, Bednarski T, Białas P, et al. Compressive sensing of signals generated in plastic scintillators in a novel J-PET instrument. Nucl. Instrum. Meth. Phys. Res. A. 2015;786:105-12.
  • 10. Moskal P, Rundel O, Alfs D, Bednarski T, Białas P, Czerwiński E, et al. Time resolution of the plastic scintillator strips with matrix photomultiplier readout for J-PET tomograph. Phys. Med. Biol. 2016;61:2025-47.
  • 11. Niedźwiecki S, Białas P, Curceanu C, Czerwiński E, Dulski K, Gajos A, et al. J-PET: A New Technology for the Whole-body PET Imaging. Acta Phys. Polon. B. 2017;48:1567-76.
  • 12. Jan S, Santin G, Strul D, Staelens S, Assie K, Autret D, et al. GATE: a simulation toolkit for PET and SPECT. Phys. Med. Biol. 2004;49:4543-62.
  • 13. Sarrut D, Bała M, Bardiès M, Bert J, Chauvin M, Chatzipapas K, et al. Advanced Monte Carlo simulations of emission tomography imaging systems with GATE. Phys. Med. Biol. 2021;66:10TR03.
  • 14. Dadgar M, Kowalski P. Gate simulation study of the 24-module J-PET scanner: Data analysis and image reconstruction. Acta Physica Polonica B. 2020;51:309-15.
  • 15. Baran J, Krzemień W, Raczyński L, Bala M, Coussat A, Parzych S, et al. Realistic Total-Body J-PET Geometry Optimization - Monte Carlo Study. arXiv preprint. 2022;arXiv:2212.02285.
  • 16. NEMA Standards Publication NU 2-2007: Performance measurements of Positron Emission Tomographs. Nat. Elect. Manuf. Assoc. Available from: https://psec.uchicago.edu/library/applications/PET/chien_min_NEMA_NU2_2007.pd.
  • 17. Parzych S. Optimization of positronium imaging performance of simulated Modular J-PET scanner using GATE software. Symposium on new trends in nuclear and medical physics; 2023 Oct 18-20; Kraków. Poland; 2023.
Uwagi
Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-c49f3908-7835-4434-837f-9ea5ac2f0bda
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.