دورية أكاديمية
أعرض في EDS

Manual Versus Artificial Intelligence-Based Segmentations as a Pre-processing Step in Whole-body PET Dosimetry Calculations.

التفاصيل البيبلوغرافية
العنوان: Manual Versus Artificial Intelligence-Based Segmentations as a Pre-processing Step in Whole-body PET Dosimetry Calculations.
المؤلفون: van Sluis J; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands. j.van.sluis@umcg.nl., Noordzij W; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., de Vries EGE; Department of Medical Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., Kok IC; Department of Medical Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., de Groot DJA; Department of Medical Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., Jalving M; Department of Medical Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., Lub-de Hooge MN; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.; Department of Clinical Pharmacy and Pharmacology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., Brouwers AH; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands., Boellaard R; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.; Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
المصدر: Molecular imaging and biology [Mol Imaging Biol] 2023 Apr; Vol. 25 (2), pp. 435-441. Date of Electronic Publication: 2022 Oct 04.
نوع المنشور: Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: Springer Country of Publication: United States NLM ID: 101125610 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1860-2002 (Electronic) Linking ISSN: 15361632 NLM ISO Abbreviation: Mol Imaging Biol Subsets: MEDLINE
أسماء مطبوعة: Publication: 2005- : New York, NY : Springer
Original Publication: New York, NY : Elsevier Science, c2001-
مواضيع طبية MeSH: Positron Emission Tomography Computed Tomography* , Positron-Emission Tomography*/methods, Humans ; Artificial Intelligence ; Tissue Distribution ; Pilot Projects ; Radiometry/methods
مستخلص: Purpose: As novel tracers are continuously under development, it is important to obtain reliable radiation dose estimates to optimize the amount of activity that can be administered while keeping radiation burden within acceptable limits. Organ segmentation is required for quantification of specific uptake in organs of interest and whole-body dosimetry but is a time-consuming task which induces high interobserver variability. Therefore, we explored using manual segmentations versus an artificial intelligence (AI)-based automated segmentation tool as a pre-processing step for calculating whole-body effective doses to determine the influence of variability in volumetric whole-organ segmentations on dosimetry.
Procedures: PET/CT data of six patients undergoing imaging with 89 Zr-labelled pembrolizumab were included. Manual organ segmentations were performed, using in-house developed software, and biodistribution information was obtained. Based on the activity biodistribution information, residence times were calculated. The residence times served as input for OLINDA/EXM version 1.0 (Vanderbilt University, 2003) to calculate the whole-body effective dose (mSv/MBq). Subsequently, organ segmentations were performed using RECOMIA, a cloud-based AI platform for nuclear medicine and radiology research. The workflow for calculating residence times and whole-body effective doses, as described above, was repeated.
Results: Data were acquired on days 2, 4, and 7 post-injection, resulting in 18 scans. Overall analysis time per scan was approximately 4 h for manual segmentations compared to ≤ 30 min using AI-based segmentations. Median Jaccard similarity coefficients between manual and AI-based segmentations varied from 0.05 (range 0.00-0.14) for the pancreas to 0.78 (range 0.74-0.82) for the lungs. Whole-body effective doses differed minimally for the six patients with a median difference in received mSv/MBq of 0.52% (range 0.15-1.95%).
Conclusion: This pilot study suggests that whole-body dosimetry calculations can benefit from fast, automated AI-based whole organ segmentations.
(© 2022. The Author(s).)
References: EJNMMI Res. 2021 Jun 7;11(1):53. (PMID: 34100117)
Ann ICRP. 2007;37(2-4):1-332. (PMID: 18082557)
EJNMMI Phys. 2015 Dec;2(1):5. (PMID: 26501807)
Sci Rep. 2020 Aug 13;10(1):13724. (PMID: 32792540)
EJNMMI Phys. 2016 Dec;3(1):13. (PMID: 27447823)
J Nucl Med. 2005 Jun;46(6):1023-7. (PMID: 15937315)
IEEE Trans Med Imaging. 2009 Jul;28(7):1000-10. (PMID: 19131298)
Eur J Nucl Med Mol Imaging. 2009 Oct;36(10):1639-50. (PMID: 19437012)
Med Phys. 2014 Oct;41(10):102503. (PMID: 25281978)
Eur J Nucl Med Mol Imaging. 2010 Jun;37(6):1238-50. (PMID: 20411259)
Nucl Med Mol Imaging. 2016 Jun;50(2):104-11. (PMID: 27275358)
EJNMMI Phys. 2020 Aug 4;7(1):51. (PMID: 32754893)
J Med Imaging (Bellingham). 2016 Oct;3(4):043502. (PMID: 27921070)
J Nucl Med. 2014 Feb;55(2):264-7. (PMID: 24357686)
معلومات مُعتمدة: 116106 HORIZON EUROPE Reforming and enhancing the European Research and Innovation system
فهرسة مساهمة: Keywords: Artificial intelligence; Dosimetry; Segmentation
تواريخ الأحداث: Date Created: 20221004 Date Completed: 20230314 Latest Revision: 20230413
رمز التحديث: 20230414
مُعرف محوري في PubMed: PMC10006025
DOI: 10.1007/s11307-022-01775-5
PMID: 36195742
قاعدة البيانات: MEDLINE
الوصف
تدمد:1860-2002
DOI:10.1007/s11307-022-01775-5