دورية أكاديمية
أعرض في EDS

Holistic evaluation of a machine learning-based timing calibration for PET detectors under varying data sparsity.

التفاصيل البيبلوغرافية
العنوان: Holistic evaluation of a machine learning-based timing calibration for PET detectors under varying data sparsity.
المؤلفون: Naunheim S; Physics of Molecular Imaging Systems, RWTH Aachen University, Pauwelsstrasse 19, Aachen, 52074, GERMANY., Mueller F; Physics of Molecular Imaging Systems, RWTH Aachen University, Paulwelsstrasse 19, Aachen, 52074, GERMANY., Nadig V; Physics of Molecular Imaging Systems, RWTH Aachen University, Pauwelsstrasse 17, Aachen, 52074, GERMANY., Kuhl Y; Experimental Molecular Imaging, Physics of Molecular Imaging Systems, RWTH Aachen University, Pauwelsstr. 19, Aachen, 52074, GERMANY., Breuer J; Molecular Imaging, Siemens Healthcare GmbH Forchheim, Siemensstraße 1, Forchheim, Bayern, 91301, GERMANY., Zhang N; Siemens Medical Solutions USA Inc., Molecular Imaging, Knoxville, Knoxville, Tennessee, 37853, UNITED STATES., Cho S; Siemens Medical Solutions USA Inc., Molecular Imaging, Knoxville, Knoxville, Tennessee, 37853, UNITED STATES., Kapusta M; Siemens Medical Solutions USA Inc., Molecular Imaging, Knoxville, Knoxville, Tennessee, 37853, UNITED STATES., Mintzer R; Siemens Medical Solutions USA, Inc., Knoxville, Knoxville, Tennessee, 37853, UNITED STATES., Judenhofer M; Molecular Imaging, Siemens Medical Solutions USA Inc., Knoxville, Knoxville, Tennessee, 37853, UNITED STATES., Schulz V; Physics of Molecular Imaging Systems, RWTH Aachen University, Pauwelsstrasse 19, Aachen, 52074, GERMANY.
المصدر: Physics in medicine and biology [Phys Med Biol] 2024 Jul 16. Date of Electronic Publication: 2024 Jul 16.
Publication Model: Ahead of Print
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: IOP Publishing Country of Publication: England NLM ID: 0401220 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1361-6560 (Electronic) Linking ISSN: 00319155 NLM ISO Abbreviation: Phys Med Biol Subsets: MEDLINE
أسماء مطبوعة: Original Publication: Bristol : IOP Publishing
مستخلص: Objective: Modern PET scanners offer precise TOF information, improving the SNR of the reconstructed images. Timing calibrations are performed to reduce the worsening effects of the system components and provide valuable TOF information. Traditional calibration procedures often provide static or linear corrections, with the drawback that higher-order skews or event-to-event corrections are not addressed. Novel research demonstrated significant improvements in the reachable timing resolutions when combining conventional calibration approaches with machine learning, with the disadvantage of extensive calibration times infeasible for a clinical application. In this work, we made the first steps towards an in-system application and analyzed the effects of varying data sparsity on a machine learning timing calibration, aiming to accelerate the calibration time. Furthermore, we demonstrated the versatility of our calibration concept by applying the procedure for the first time to analog readout technology. Approach. We modified experimentally acquired calibration data used for training regarding their statistical and spatial sparsity, mimicking reduced measurement time and variability of the training data. Trained models were tested on unseen test data, characterized by fine spatial sampling and rich statistics. In total, 80 decision tree models with the same hyperparameter settings, were trained and holistically evaluated regarding data scientific, physics-based, and PET-based quality criteria. Main results. The calibration procedure can be heavily reduced from several days to some minutes without sacrificing quality and still significantly improving the timing resolution from (304 ± 5) ps to (216 ± 1) ps compared to conventionally used analytical calibration methods. Significance. This work serves as the first step in making the developed machine learning-based calibration suitable for an in-system application to profit from the method's capabilities on the system level. Furthermore, this work demonstrates the functionality of the methodology on detectors using analog readout technology. The proposed holistic evaluation criteria here serve as a guideline for future evaluations of machine learning-based calibration approaches. .
(Creative Commons Attribution license.)
فهرسة مساهمة: Keywords: CTR; Gradient-Boosted Decision Trees; Machine Learning; PET; Residual Physics; TOF
تواريخ الأحداث: Date Created: 20240716 Latest Revision: 20240716
رمز التحديث: 20240717
DOI: 10.1088/1361-6560/ad63ec
PMID: 39013414
قاعدة البيانات: MEDLINE
الوصف
تدمد:1361-6560
DOI:10.1088/1361-6560/ad63ec