دورية أكاديمية
Deep transformer-based personalized dosimetry from SPECT/CT images: a hybrid approach for [ 177 Lu]Lu-DOTATATE radiopharmaceutical therapy.
| العنوان: | Deep transformer-based personalized dosimetry from SPECT/CT images: a hybrid approach for [ 177 Lu]Lu-DOTATATE radiopharmaceutical therapy. |
|---|---|
| المؤلفون: | Mansouri Z; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland., Salimi Y; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland., Akhavanallaf A; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland., Shiri I; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland., Teixeira EPA; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland., Hou X; Department of Radiology, University of British Columbia, Vancouver, BC, Canada., Beauregard JM; Cancer Research Centre and Department of Radiology and Nuclear Medicine, Université Laval, Quebec City, QC, Canada., Rahmim A; Department of Radiology, University of British Columbia, Vancouver, BC, Canada., Zaidi H; Division of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland. habib.zaidi@hcuge.ch.; Department of Nuclear Medicine, University Medical Center Groningen, University of Groningen, 9700 RB, Groningen, Netherlands. habib.zaidi@hcuge.ch.; Department of Nuclear Medicine, University of Southern Denmark, DK-500, Odense, Denmark. habib.zaidi@hcuge.ch.; University Research and Innovation Center, Óbuda University, Budapest, Hungary. habib.zaidi@hcuge.ch. |
| المصدر: | European journal of nuclear medicine and molecular imaging [Eur J Nucl Med Mol Imaging] 2024 May; Vol. 51 (6), pp. 1516-1529. Date of Electronic Publication: 2024 Jan 25. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Springer-Verlag Berlin Country of Publication: Germany NLM ID: 101140988 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1619-7089 (Electronic) Linking ISSN: 16197070 NLM ISO Abbreviation: Eur J Nucl Med Mol Imaging Subsets: MEDLINE |
| أسماء مطبوعة: | Original Publication: Berlin : Springer-Verlag Berlin, 2002- |
| مواضيع طبية MeSH: | Octreotide*/*analogs & derivatives, Octreotide*/therapeutic use , Organometallic Compounds*/therapeutic use , Single Photon Emission Computed Tomography Computed Tomography*/methods , Radiometry*/methods , Radiopharmaceuticals*/therapeutic use, Humans ; Precision Medicine/methods ; Deep Learning ; Male ; Female ; Monte Carlo Method ; Image Processing, Computer-Assisted/methods ; Neuroendocrine Tumors/radiotherapy ; Neuroendocrine Tumors/diagnostic imaging |
| مستخلص: | Purpose: Accurate dosimetry is critical for ensuring the safety and efficacy of radiopharmaceutical therapies. In current clinical dosimetry practice, MIRD formalisms are widely employed. However, with the rapid advancement of deep learning (DL) algorithms, there has been an increasing interest in leveraging the calculation speed and automation capabilities for different tasks. We aimed to develop a hybrid transformer-based deep learning (DL) model that incorporates a multiple voxel S-value (MSV) approach for voxel-level dosimetry in [ 177 Lu]Lu-DOTATATE therapy. The goal was to enhance the performance of the model to achieve accuracy levels closely aligned with Monte Carlo (MC) simulations, considered as the standard of reference. We extended our analysis to include MIRD formalisms (SSV and MSV), thereby conducting a comprehensive dosimetry study. Methods: We used a dataset consisting of 22 patients undergoing up to 4 cycles of [ 177 Lu]Lu-DOTATATE therapy. MC simulations were used to generate reference absorbed dose maps. In addition, MIRD formalism approaches, namely, single S-value (SSV) and MSV techniques, were performed. A UNEt TRansformer (UNETR) DL architecture was trained using five-fold cross-validation to generate MC-based dose maps. Co-registered CT images were fed into the network as input, whereas the difference between MC and MSV (MC-MSV) was set as output. DL results are then integrated to MSV to revive the MC dose maps. Finally, the dose maps generated by MSV, SSV, and DL were quantitatively compared to the MC reference at both voxel level and organ level (organs at risk and lesions). Results: The DL approach showed slightly better performance (voxel relative absolute error (RAE) = 5.28 ± 1.32) compared to MSV (voxel RAE = 5.54 ± 1.4) and outperformed SSV (voxel RAE = 7.8 ± 3.02). Gamma analysis pass rates were 99.0 ± 1.2%, 98.8 ± 1.3%, and 98.7 ± 1.52% for DL, MSV, and SSV approaches, respectively. The computational time for MC was the highest (~2 days for a single-bed SPECT study) compared to MSV, SSV, and DL, whereas the DL-based approach outperformed the other approaches in terms of time efficiency (3 s for a single-bed SPECT). Organ-wise analysis showed absolute percent errors of 1.44 ± 3.05%, 1.18 ± 2.65%, and 1.15 ± 2.5% for SSV, MSV, and DL approaches, respectively, in lesion-absorbed doses. Conclusion: A hybrid transformer-based deep learning model was developed for fast and accurate dose map generation, outperforming the MIRD approaches, specifically in heterogenous regions. The model achieved accuracy close to MC gold standard and has potential for clinical implementation for use on large-scale datasets. (© 2024. The Author(s).) |
| References: | Cancers (Basel). 2022 Jul 14;14(14):. (PMID: 35884478) Ann Nucl Med. 2022 Feb;36(2):133-143. (PMID: 35029818) J Nucl Med. 1999 Jan;40(1):11S-36S. (PMID: 9935083) PET Clin. 2021 Oct;16(4):627-641. (PMID: 34537133) Nuklearmedizin. 2023 Dec;62(6):379-388. (PMID: 37827503) Nat Rev Drug Discov. 2020 Sep;19(9):589-608. (PMID: 32728208) Eur J Nucl Med Mol Imaging. 2013 May;40(5):800-16. (PMID: 23389427) Eur J Nucl Med Mol Imaging. 2022 Sep;49(11):3830-3840. (PMID: 35451612) Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961) J Nucl Med. 1971 Mar;:Suppl 5:5-23. (PMID: 5551700) Annu Rev Biomed Eng. 2021 Jul 13;23:249-276. (PMID: 33797938) Med Phys. 2019 Nov;46(11):5284-5293. (PMID: 31461537) Med Image Anal. 2022 Jul;79:102470. (PMID: 35576821) EJNMMI Phys. 2019 Mar 4;6(1):4. (PMID: 30830530) Med Phys. 2023 Feb;50(2):e1-e24. (PMID: 36565447) Eur J Nucl Med Mol Imaging. 2021 Mar;48(3):670-682. (PMID: 32875430) Cancers (Basel). 2011 Oct 11;3(4):3838-55. (PMID: 24213114) Phys Med Biol. 2019 Aug 28;64(17):175006. (PMID: 31287093) EJNMMI Phys. 2018 Oct 15;5(1):25. (PMID: 30318563) J Clin Oncol. 2008 May 1;26(13):2124-30. (PMID: 18445841) Nucl Med Mol Imaging. 2023 Apr;57(2):94-102. (PMID: 36998593) EJNMMI Res. 2018 Aug 29;8(1):89. (PMID: 30159614) EJNMMI Res. 2019 Aug 14;9(1):76. (PMID: 31414241) Phys Med. 2024 Jan;117:103192. (PMID: 38052710) Sci Rep. 2019 Jul 16;9(1):10308. (PMID: 31311963) Eur J Radiol. 2023 Dec;169:111159. (PMID: 37976760) J Nucl Med. 2021 Dec;62(Suppl 3):36S-47S. (PMID: 34857620) Med Dosim. 1996 Spring;21(1):19-22. (PMID: 8679066) Eur J Nucl Med Mol Imaging. 2014 Oct;41(10):1976-88. (PMID: 24915892) EJNMMI Phys. 2019 Dec 30;6(1):31. (PMID: 31889238) Med Phys. 2019 Dec;46(12):5403-5406. (PMID: 31584697) J Nucl Med. 2012 Aug;53(8):1310-25. (PMID: 22743252) Phys Med Biol. 2020 Feb 04;65(3):035007. (PMID: 31881547) N Engl J Med. 2017 Jan 12;376(2):125-135. (PMID: 28076709) Phys Med Biol. 2000 Feb;45(2):459-78. (PMID: 10701515) J Nucl Med. 2022 Nov;63(11):1665-1672. (PMID: 35422445) Phys Med. 2021 Mar;83:122-137. (PMID: 33765602) Med Phys. 2022 Feb;49(2):1216-1230. (PMID: 34882821) Eur J Nucl Med Mol Imaging. 2022 Nov;49(13):4452-4463. (PMID: 35809090) Ann Nucl Med. 2020 Apr;34(4):244-253. (PMID: 32114682) J Nucl Med. 2009 Mar;50(3):477-84. (PMID: 19258258) Med Phys. 1996 Sep;23(9):1523-9. (PMID: 8892249) J Nucl Med. 2018 Jul;59(7):1133-1139. (PMID: 29242397) |
| معلومات مُعتمدة: | Sinfonia project under grant agreement No 945196 H2020 Euratom |
| فهرسة مساهمة: | Keywords: Deep learning; Monte Carlo simulation; Radiation dosimetry; Radionuclide therapy; [177Lu]Lu-DOTATATE |
| المشرفين على المادة: | RWM8CCW8GP (Octreotide) AE221IM3BB (lutetium Lu 177 dotatate) 0 (Organometallic Compounds) 0 (Radiopharmaceuticals) |
| تواريخ الأحداث: | Date Created: 20240124 Date Completed: 20240424 Latest Revision: 20240427 |
| رمز التحديث: | 20240427 |
| مُعرف محوري في PubMed: | PMC11043201 |
| DOI: | 10.1007/s00259-024-06618-9 |
| PMID: | 38267686 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Springer Verlag. 
Full Text Finder | تدمد: | 1619-7089 |
|---|---|
| DOI: | 10.1007/s00259-024-06618-9 |