A radiomic- and dosiomic-based machine learning regression model for pretreatment planning in
177Lu-DOTATATE
dose prediction model
dosimetry
dosiomics
machine learning
radiomics
radiotoxicity
regression model
treatment planning
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Nov 2023
Nov 2023
Historique:
revised:
01
09
2023
received:
16
12
2022
accepted:
07
09
2023
medline:
6
11
2023
pubmed:
19
9
2023
entrez:
18
9
2023
Statut:
ppublish
Résumé
Standardized patient-specific pretreatment dosimetry planning is mandatory in the modern era of nuclear molecular radiotherapy, which may eventually lead to improvements in the final therapeutic outcome. Only a comprehensive definition of a dosage therapeutic window encompassing the range of absorbed doses, that is, helpful without being detrimental can lead to therapy individualization and improved outcomes. As a result, setting absorbed dose safety limits for organs at risk (OARs) requires knowledge of the absorbed dose-effect relationship. Data sets of consistent and reliable inter-center dosimetry findings are required to characterize this relationship. We developed and standardized a new pretreatment planning model consisting of a predictive dosimetry procedure for OARs in patients with neuroendocrine tumors (NETs) treated with Pretreatment and posttreatment data for 20 patients with NETs treated with We evaluated nine ML regression algorithms. Our predictive model achieved a mean absolute dose error (MAE, in Gy) of 0.61 for the liver, 1.58 for the spleen, 1.30 for the left kidney, and 1.35 for the right kidney between pretherapy The combination of radiomics and dosiomics has potential utility for personalized molecular radiotherapy (PMR) response evaluation and OAR dose prediction. These radiodosiomic features can potentially provide information on any possible disease recurrence and may be highly useful in clinical decision-making, especially regarding dose escalation issues.
Sections du résumé
BACKGROUND
BACKGROUND
Standardized patient-specific pretreatment dosimetry planning is mandatory in the modern era of nuclear molecular radiotherapy, which may eventually lead to improvements in the final therapeutic outcome. Only a comprehensive definition of a dosage therapeutic window encompassing the range of absorbed doses, that is, helpful without being detrimental can lead to therapy individualization and improved outcomes. As a result, setting absorbed dose safety limits for organs at risk (OARs) requires knowledge of the absorbed dose-effect relationship. Data sets of consistent and reliable inter-center dosimetry findings are required to characterize this relationship.
PURPOSE
OBJECTIVE
We developed and standardized a new pretreatment planning model consisting of a predictive dosimetry procedure for OARs in patients with neuroendocrine tumors (NETs) treated with
METHODS
METHODS
Pretreatment and posttreatment data for 20 patients with NETs treated with
RESULTS
RESULTS
We evaluated nine ML regression algorithms. Our predictive model achieved a mean absolute dose error (MAE, in Gy) of 0.61 for the liver, 1.58 for the spleen, 1.30 for the left kidney, and 1.35 for the right kidney between pretherapy
CONCLUSIONS
CONCLUSIONS
The combination of radiomics and dosiomics has potential utility for personalized molecular radiotherapy (PMR) response evaluation and OAR dose prediction. These radiodosiomic features can potentially provide information on any possible disease recurrence and may be highly useful in clinical decision-making, especially regarding dose escalation issues.
Substances chimiques
copper dotatate CU-64
0
Octreotide
RWM8CCW8GP
Organometallic Compounds
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7222-7235Subventions
Organisme : European Union's Horizon 2020 research and innovation programme
Organisme : European Regional Development Fund
Organisme : Hellenic Foundation for Research and Innovation
Informations de copyright
© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.
Références
Bodei L, Kidd M, Baum RP, Modlin IM. PRRT: defining the paradigm shift to achieve standardization and individualization. J Nucl Med. 2014;55(11):1753-1756.
Del Olmo-Garcia MI, Prado-Wohlwend S, Bello P, Segura A, Merino-Torres JF. Peptide receptor radionuclide therapy with [(177)Lu]Lu-DOTA-TATE in patients with advanced GEP NENS: present and future directions. Cancers (Basel). 2022;14(3):584.
Puliani G, Chiefari A, Mormando M, Bianchini M, Lauretta R, Appetecchia M. New Insights in PRRT: lessons from 2021. Front Endocrinol (Lausanne). 2022;13:861434.
Plachouris D, Mountris KA, Papadimitroulas P, et al. Clinical evaluation of a three-dimensional internal dosimetry technique for liver radioembolization with (90)Y microspheres using dose Voxel Kernels. Cancer Biother Radiopharm. 2021;36(10):809-819.
Lu X, Lu C, Yang Y, et al. Current status and trends in peptide receptor radionuclide therapy in the past 20 years (2000-2019): a bibliometric study. Front. Pharmacol. 2021;12:624534.
Sgouros G, Dewaraja YK, Escorcia F, et al. Tumor response to radiopharmaceutical therapies: the knowns and the unknowns. J Nucl Med. 2021;62(suppl 3):12S-22S.
Sandstrom M, Garske-Roman U, Granberg D, et al. Individualized dosimetry of kidney and bone marrow in patients undergoing Lu-177-DOTA-Octreotate treatment. J Nucl Med. 2013;54(1):33-41.
Sundlov A, Sjogreen-Gleisner K, Svensson J, et al. Individualised (177)Lu-DOTATATE treatment of neuroendocrine tumours based on kidney dosimetry [published online ahead of print 20170322]. Eur J Nucl Med Mol Imaging. 2017;44(9):1480-1489.
Sundlov A, Gleisner KS, Tennvall J, et al. Phase II trial demonstrates the efficacy and safety of individualized, dosimetry-based (177)Lu-DOTATATE treatment of NET patients [published online ahead of print 20220422]. Eur J Nucl Med Mol Imaging. 2022;49(11):3830-3840.
Svensson J, Berg G, Wangberg B, Larsson M, Forssell-Aronsson E, Bernhardt P. Renal function affects absorbed dose to the kidneys and haematological toxicity during (1)(7)(7)Lu-DOTATATE treatment [published online ahead of print 20150206]. Eur J Nucl Med Mol Imaging. 2015;42(6):947-955.
Yao JC, Hassan M, Phan A, et al. One hundred years after “carcinoid”: epidemiology of and prognostic factors for neuroendocrine tumors in 35,825 cases in the United States. J Clin Oncol. 2008;26(18):3063-3072.
Ahmed A, Turner G, King B, et al. Midgut neuroendocrine tumours with liver metastases: results of the UKINETS study [published online ahead of print 2009/05/22]. Endocr Relat Cancer. 2009;16(3):885-894.
Modlin IM, Kidd M, Latich I, Zikusoka MN, Shapiro MD. Current status of gastrointestinal carcinoids [published online ahead of print 2005/05/12]. Gastroenterology. 2005;128(6):1717-1751.
Kwekkeboom DJ, de Herder WW, Kam BL, et al. Treatment with the radiolabeled somatostatin analog [177 Lu-DOTA 0,Tyr3]octreotate: toxicity, efficacy, and survival. J Clin Oncol. 2008;26(13):2124-2130.
Strosberg J, El-Haddad G, Wolin E, et al. Phase 3 trial of (177)lu-dotatate for midgut neuroendocrine tumors. N Engl J Med. 2017;376(2):125-135.
Strosberg JR, Caplin ME, Kunz PL, et al. Final overall survival in the phase 3 NETTER-1 study of lutetium-177-DOTATATE in patients with midgut neuroendocrine tumors. J. Clin. Oncol. 2021;39(15_suppl):4112.
Kwekkeboom DJ, Teunissen JJ, Bakker WH, et al. Radiolabeled somatostatin analog [177Lu-DOTA0,Tyr3]octreotate in patients with endocrine gastroenteropancreatic tumors. J Clin Oncol. 2005;23(12):2754-2762.
Jahn U, Ilan E, Sandstrom M, Lubberink M, Garske-Roman U, Sundin A. Peptide receptor radionuclide therapy (PRRT) with Lu-177-DOTATATE; differences in tumor dosimetry, vascularity and lesion metrics in pancreatic and small intestinal neuroendocrine neoplasms. Cancers. 2021;13(5):962.
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441-446.
Patyk M, Silicki J, Mazur R, Krecichwost R, Sokolowska-Dabek D, Zaleska-Dorobisz U. Radiomics-the value of the numbers in present and future radiology. Pol J Radiol. 2018;83:e171-e174.
Papadimitroulas P, Brocki L, Christopher Chung N, et al. Artificial intelligence: deep learning in oncological radiomics and challenges of interpretability and data harmonization. Phys Med. 2021;83:108-121.
Visvikis D, Cheze Le Rest C, Jaouen V, Hatt M. Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications. Eur J Nucl Med Mol Imaging. 2019;46(13):2630-2637.
Gabrys HS, Buettner F, Sterzing F, Hauswald H, Bangert M. Design and selection of machine learning methods using radiomics and dosiomics for normal tissue complication probability modeling of Xerostomia. Front. Oncol. 2018;8:35.
Liang B, Yan H, Tian Y, et al. Dosiomics: extracting 3D spatial features from dose distribution to predict incidence of radiation pneumonitis. Front Oncol. 2019;9:269.
Chopra N, Dou T, Sharp G, Sajo E, Mak RH. A combined radiomics-dosiomics machine learning approach improves prediction of radiation pneumonitis compared to DVH data in lung cancer patients. Int J Radiat Oncol Biol Phys. 2020;108:e777.
Hatt M, Krizsan AK, Rahmim A, et al. Joint EANM/SNMMI guideline on radiomics in nuclear medicine : jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council [published online ahead of print 20221103]. Eur J Nucl Med Mol Imaging. 2023;50(2):352-375.
Qin Y, Zhu LH, Zhao W, Wang JJ, Wang H. Review of radiomics- and dosiomics-based predicting models for rectal cancer [published online ahead of print 20220809]. Front Oncol. 2022;12:913683.
Wang B, Liu J, Zhang X, et al. Prognostic value of (18)F-FDG PET/CT-based radiomics combining dosiomics and dose volume histogram for head and neck cancer [published online ahead of print 20230213]. EJNMMI Res. 2023;13(1):14.
Baum RP, Kulkarni HR, Singh A, et al. Results and adverse events of personalized peptide receptor radionuclide therapy with (90)Yttrium and (177)Lutetium in 1048 patients with neuroendocrine neoplasms. Oncotarget. 2018;9(24):16932-16950.
Kesavan M, Turner JH. Myelotoxicity of peptide receptor radionuclide therapy of neuroendocrine tumors: a decade of experience. Cancer Biother Radiopharm. 2016;31(6):189-198.
Sabet A, Ezziddin K, Pape UF, et al. Long-term hematotoxicity after peptide receptor radionuclide therapy with Lu-177-Octreotate. J Nucl Med. 2013;54(11):1857-1861.
Arabi H, Zaidi H. Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy. Eur J Hybrid Imag. 2020;4(1):17.
Mazurowski MA. Artificial intelligence may cause a significant disruption to the radiology workforce. J Am Coll Radiol. 2019;16(8):1077-1082.
Yi PH, Hui FK, Ting DSW. Artificial intelligence and radiology: collaboration is key. J Am Coll Radiol. 2018;15(5):781-783.
Decuyper M, Maebe J, Van Holen R, Vandenberghe S. Artificial intelligence with deep learning in nuclear medicine and radiology. Ejnmmi Phys. 2021;8(1):81.
Plachouris D, Tzolas I, Gatos I, et al. A deep-learning-based prediction model for the biodistribution of (90) Y microspheres in liver radioembolization. Med Phys. 2021;48(11):7427-7438.
Chicheportiche A, Grozinsky-Glasberg S, Gross DJ, et al. Predictive power of the post-treatment scans after the initial or first two courses of [Lu-177]-DOTA-TATE. Ejnmmi Phys. 2018;5(1):36.
Akhavanallaf A, Peterson AB, Fitzpatrick K, et al. The predictive value of pretherapy [(68)Ga]Ga-DOTA-TATE PET and biomarkers in [(177)Lu]Lu-PRRT tumor dosimetry [published online ahead of print 20230512]. Eur J Nucl Med Mol Imaging. 2023;50(10):2984-2996.
Bruvoll R, Blakkisrud J, Mikalsen LT, Connelly J, Stokke C. Correlations between [(68)Ga]Ga-DOTA-TOC Uptake and Absorbed Dose from [(177)Lu]Lu-DOTA-TATE [published online ahead of print 20230210]. Cancers (Basel). 2023;15(4):1134.
Kratochwil C, Stefanova M, Mavriopoulou E, et al. SUV of [68Ga]DOTATOC-PET/CT predicts response probability of prrt in neuroendocrine tumors. Mol Imaging Biol. 2015;17(3):313-318.
Sharma R, Wang WM, Yusuf S, et al. Ga-DOTATATE PET/CT parameters predict response to peptide receptor radionuclide therapy in neuroendocrine tumours. Radiother Oncol. 2019;141:108-115.
Thuillier P, Maajem M, Schick U, et al. Clinical assessment of 177Lu-DOTATATE quantification by comparison of SUV-based parameters measured on both Post-PRRT SPECT/CT and 68Ga-DOTATOC PET/CT in patients with neuroendocrine tumors: a feasibility study. Clin Nucl Med. 2021;46(2):111-118.
Ezziddin S, Lohmar J, Yong-Hing CJ, et al. Does the pretherapeutic tumor SUV in 68Ga DOTATOC PET predict the absorbed dose of 177Lu octreotate? Clin Nucl Med. 2012;37(6):e141-147.
Kim YI, Oh J, Yoo C, Ryoo BY, Ryu JS. Prediction of absorbed dose by tumors and critical organs after Lu-177-DOTATATE therapy using pretherapeutic Ga-68-DOTATOC PET/CT. J Nucl Med. 2021;62(supplement 1):76.
Wong KK, Frey KA, Niedbala J, et al. Differences in tumor-to-normal organ SUV ratios measured with 68 Ga-DOTATATE PET compared with 177 Lu-DOTATATE SPECT in patients with neuroendocrine tumors [published online ahead of print 20220610]. Nucl Med Commun. 2022;43(8):892-900.
Vergnaud L, Giraudet AL, Moreau A, et al. Patient-specific dosimetry adapted to variable number of SPECT/CT time-points per cycle for [Formula: see text]Lu-DOTATATE therapy [published online ahead of print 2022/05/17]. Ejnmmi Phys. 2022;9(1):37.
Dewaraja YK, Frey EC, Sgouros G, et al. MIRD pamphlet No. 23: quantitative SPECT for patient-specific 3-dimensional dosimetry in internal radionuclide therapy [published online ahead of print 20120628]. J Nucl Med. 2012;53(8):1310-1325.
Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine Learning in Python. J Mach Learn Res. 2011;12:2825-2830.
Chen T, Guestrin C. XGBoost: a Scalable Tree Boosting System. 22nd SIGKDD Conference on Knowledge Discovery and Data Mining; 2016:785-794.
Van Rossum G, Drake Jr FL. Python Reference Manual. Centrum voor Wiskunde en Informatica; 1995.
van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77(21):E104-E107.
Hatt M, Vallieres M, Visvikis D, Zwanenburg A. IBSI: an international community radiomics standardization initiative. J Nucl Med. 2018;59(supplement 1):287.
Afshar P, Mohammadi A, Plataniotis KN, Oikonomou A, Benali H. From handcrafted to deep-learning-based cancer radiomics challenges and opportunities. IEEE Signal Proc Mag. 2019;36(4):132-160.
Lipton ZC. The Mythos of model interpretability. Commun ACM. 2018;61(10):36-43.
P4P. Pearson's correlation coefficient. In: Kirch W, ed. Encyclopedia of Public Health; 2008.
Shannon C. A mathematical theory of communication. ACM SIGMOBILE Mobile Comput Commun Rev. 2001;5(1):3-55.
Kullback S, Leibler RA. On information and sufficiency. Ann Math Statist. 1951;22(1):79-86.
LOOCV. Leave-One-Out cross-validation. In: C/S, ed. Encyclopedia of Machine Learning. Springer; 2011.
Willmott CJ, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res. 2005;30(1):79-82.
Sarrut D, Bardies M, Boussion N, et al. A review of the use and potential of the GATE Monte Carlo simulation code for radiation therapy and dosimetry applications. Med Phys. 2014;41(6):064301.
Sarrut D, Arbor N, Baudier T, et al. The OpenGATE ecosystem for Monte Carlo simulation in medical physics [published online ahead of print 20220908]. Phys Med Biol. 2022;67(18):184001.
Computing YA. High-Performance Computing (HPC) Center. Accessed July 21, 2023. https://www.yac.hr/
Webb GI. Encyclopedia of Machine Learning. Springer; 2010.
Bodei L, Cremonesi M, Ferrari M, et al. Long-term evaluation of renal toxicity after peptide receptor radionuclide therapy with Y-90-DOTATOC and Lu-177-DOTATATE: the role of associated risk factors. Eur J Nucl Med Mol I. 2008;35(10):1847-1856.
Frilling A, Modlin IM, Kidd M, et al. Recommendations for management of patients with neuroendocrine liver metastases. Lancet Oncol. 2014;15(1):E8-E21.
Kwekkeboom DJ, Mueller-Brand J, Paganelli G, et al. Overview of results of peptide receptor radionuclide therapy with 3 radiolabeled somatostatin analogs. J Nucl Med. 2005;46:62s-66s.
Sabet A, Dautzenberg K, Haslerud T, et al. Specific efficacy of peptide receptor radionuclide therapy with Lu-177-octreotate in advanced neuroendocrine tumours of the small intestine. Eur J Nucl Med Mol I. 2015;42(8):1238-1246.
Peterson AB, Wang C, Wong KK, et al. 177Lu-DOTATATE theranostics: predicting renal dosimetry from pretherapy 68Ga-DOTATATE PET and clinical biomarkers [published online ahead of print 20230208]. Clin Nucl Med. 2023;48(5):393-399.
Lee MS, Hwang D, Kim JH, Lee JS. Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry. Sci Rep-Uk. 2019;9:10308.
Eleftheriadis V, Savvidis G, Paneta V, Chatzipapas K, Kagadis GC, Papadimitroulas P. A framework for prediction of personalized pediatric nuclear medical dosimetry based on Machine Learning and Monte Carlo techniques [published online ahead of print 20230315]. Phys Med Biol. 2023; 68(8):084004. doi:10.1088/1361-6560/acc4a5
Sansovini M, Severi S, Ambrosetti A, et al. Treatment with the radiolabelled somatostatin analog Lu-177-DOTATATE for advanced pancreatic neuroendocrine tumors. Neuroendocrinology. 2013;97(4):347-354.
Wehrmann C, Senftleben S, Zachert C, Muller D, Baum RP. Results of individual patient dosimetry in peptide receptor radionuclide therapy with Lu-177 DOTA-TATE and Lu-177 DOTA-NOC. Cancer Biother Radio. 2007;22(3):406-416.
Stokke C, Kvassheim M, Blakkisrud J. Radionuclides for targeted therapy: physical properties [published online ahead of print 20220825]. Molecules. 2022;27(17):5429.
Fave X, Zhang LF, Yang JZ, et al. Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer. Transl Cancer Res. 2016;5(4):349-363.
Yip SSF, Aerts HJWL. Applications and limitations of radiomics. Phys Med Biol. 2016;61(13):R150-R166.