Improving timing resolution of BGO for TOF-PET : a comparative analysis with and without deep learning
Loignon-Houle, Francis (Universitat Politècnica de València. Instituto de Instrumentación para Imagen Molecular - CSIC)
Kratochwil, Nicolaus (University of California Davis. Department of Biomedical Engineering)
Toussaint, Maxime (Université de Sherbrooke. Department of Nuclear Medicine and Radiobiology)
Lowis, Carsten (RWTH Aachen University)
Ariño-Estrada, Gerard (Institut de Física d'Altes Energies)
González Martínez, Antonio Javier (Universitat Politècnica de València. Instituto de Instrumentación para Imagen Molecular - CSIC)
Auffray, Etiennette (CERN. Department EP-CMX)
Lecomte, Roger (Université de Sherbrooke. Department of Nuclear Medicine and Radiobiology)

Date:	2025
Abstract:	Background: The renewed interest in BGO scintillators for TOF-PET is driven by the improved Cherenkov photon detection with new blue-sensitive SiPMs. However, the slower scintillation light from BGO causes significant time walk with leading edge discrimination (LED), which degrades the coincidence time resolution (CTR). To address this, a time walk correction (TWC) can be done by using the rise time measured with a second threshold. Deep learning, particularly convolutional neural networks (CNNs), can also enhance CTR by training with digitized waveforms. It remains to be explored how timing estimation methods utilizing one (LED), two (TWC), or multiple (CNN) waveform data points compare in CTR performance of BGO scintillators. Results: In this work, we compare classical experimental timing estimation methods (LED, TWC) with a CNN-based method using the signals from BGO crystals read out by NUV-HD-MT SiPMs and high-frequency electronics. For crystals, implementing TWC results in a CTR of 129 ± 2 ps FWHM, while employing the CNN yields 115 ± 2 ps FWHM, marking improvements of 18 % and 26 %, respectively, relative to the standard LED estimator. For crystals, both methods yield similar CTR (around 240 ps FWHM), offering a 15 % gain over LED. The CNN, however, exhibits better tail suppression in the coincidence time distribution. Conclusions: The higher complexity of waveform digitization needed for CNNs could potentially be mitigated by adopting a simpler two-threshold approach, which appears to currently capture most of the essential information for improving CTR in longer BGO crystals. Other innovative deep learning models and training strategies may nonetheless contribute further in a near future to harnessing increasingly discernible timing features in TOF-PET detector signals.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	Time-of-flight PET ; Fast timing ; BGO ; Time resolution ; Cherenkov ; Deep learning
Published in:	EJNMMI Physics, Vol. 12 (January 2025) , art. 2, ISSN 2197-7364

DOI: 10.1186/s40658-024-00711-6
PMID: 39821728

15 p, 2.3 MB

The record appears in these collections:
Research literature > UAB research groups literature > Research Centres and Groups (research output) > Experimental sciences > Institut de Física d’Altes Energies (IFAE)
Articles > Research articles
Articles > Published articles