Möglichkeiten zur Verbesserung der Dosimetrie und Therapieplanung in der Molekularen Radiotherapie durch maschinelles Lernen

Zusammenfassung

Die Molekulare Strahlentherapie ist eine systemische oder lokoregionäre Therapie, bei der dem Patienten ein Radionuklid oder ein radioaktiv markiertes Arzneimittel verabreicht wird. Ziel ist es, die Tumorzellen abzutöten und gleichzeitig das Normalgewebe zu schonen. Die Therapieplanung umfasst deshalb die prätherapeutische Bestimmung der zu verabreichenden Aktivitätsmenge, der Substanzmenge und der zeitlichen Abfolge möglicher die Pharmakokinetik modulierender Interventionen/Injektionen.

Der Einsatz der künstlichen Intelligenz und insbesondere des maschinellen Lernens (ML) sind in letzter Zeit immer mehr in den Fokus auch der Bildgebung und Therapie mit ionisierenden Strahlen gerückt.

In dieser Übersichtsarbeit wird ein Verfahren der individualisierten Therapieplanung für die Molekulare Strahlentherapie anhand eines Ablaufplanes vorgestellt. Dabei werden die Möglichkeiten diskutiert, durch den Einsatz von maschinellem Lernen die Therapieplanung zu verbessern.

Der Einsatz von ML besitzt ein großes Potenzial in der Dosimetrie und Behandlungsplanung in der Molekularen Strahlentherapie. Jedoch sind noch weitere Anstrengungen erforderlich, um genügend relevante Daten zu sammeln und diese mittels ML effizient zur Verbesserung der Dosimetrie und Behandlungsplanung in der Molekularen Strahlentherapie zu nutzen.

Abstract

Molecular radiotherapy is a systemic or locoregional therapy in which the patient is administered a radionuclide or a radioactively labelled drug. The aim is to kill the tumour cells while at the same time protecting the normal tissue. Therapy planning therefore includes the pretherapeutic determination of the activity to be administered, the substance quantity and the temporal sequence of possible pharmacokinetics-modulating interventions/injections.

The use of artificial intelligence and in particular machine learning (ML) has recently moved more and more into the focus of imaging and therapy with ionising radiation.

In this review, an individualised treatment planning approach for molecular radiotherapy is presented based on a flow chart. The possibilities to improve therapy planning using machine learning are discussed.

The use of ML has great potential in dosimetry and treatment planning in molecular radiotherapy. However, further efforts are needed to collect sufficient relevant data and use them efficiently with ML to improve dosimetry and treatment planning in molecular radiotherapy.

Schlüsselwörter

Molekulare Radiotherapie - Radionuklidtherapie - Therapieplanung - Dosimetrie - maschinelles Lernen - PBPK

Keywords

molecular radiotherapy - radionuclide therapy - treatment planning - dosimetry - machine learning - PBPK

• Literatur

• 1 DeNardo GL, Juweid ME, White CA. et al. Role of radiation dosimetry in radioimmunotherapy planning and treatment dosing. Crit Rev Oncol Hematol 2001; 39: 203-218
• 2 Thomas SR. Options for radionuclide therapy: from fixed activity to patient-specific treatment planning. Cancer Biother Radiopharm 2002; 17: 71-82
• 3 Bolch WE, Eckerman KF, Sgouros G. et al. MIRD Pamphlet No. 21: A Generalized Schema for Radiopharmaceutical Dosimetry—Standardization of Nomenclature. J Nucl Med 2009; 50: 477-484
• 4 Glatting G, Bardiès M, Lassmann M. Treatment Planning in Molecular Radiotherapy. Z Med Phys 2013; 23: 262-269
• 5 Strigari L, Konijnenberg M, Chiesa C. et al. The evidence base for the use of internal dosimetry in the clinical practice of molecular radiotherapy. Eur J Nucl Med Mol Imaging 2014; 41: 1976-1988
• 6 Kletting P, Kull T, Maaß C. et al. Optimized Peptide Amount and Activity for ⁹⁰Y-Labeled DOTATATE Therapy. J Nucl Med 2016; 57: 503-508
• 7 Jiménez-Franco LD, Kletting P, Beer AJ. et al. Treatment planning algorithm for peptide receptor radionuclide therapy considering multiple tumor lesions and organs at risk. Med Phys 2018; 45: 3516-3523
• 8 Jiménez-Franco LD, Kletting P, Beer AJ. et al. Prescribing Tumour Dose in Molecular Radiotherapy using a PBPK Model-based Algorithm for Individualised Treatment Planning. Eur J Nucl Med Mol Imaging 2018; 45: S183 (OP-567)
• 9 Bouffler SD. Evidence for variation in human radiosensitivity and its potential impact on radiological protection. Ann ICRP 2016; 45: 280-289
• 10 Bentzen SM, Overgaard J. Patient-to-patient variability in the expression of radiation-induced normal tissue injury. Semin Radiat Oncol 1994; 4: 68-80
• 11 Gallez B, Neveu M-A, Danhier P. et al. Manipulation of tumor oxygenation and radiosensitivity through modification of cell respiration. A critical review of approaches and imaging biomarkers for therapeutic guidance. Biochimica et Biophysica Acta (BBA) – Bioenergetics 2017; 1858: 700-711
• 12 Danhier P, De Saedeleer CJ, Karroum O. et al. Optimization of Tumor Radiotherapy With Modulators of Cell Metabolism: Toward Clinical Applications. Seminars in Radiation Oncology 2013; 23: 262-272
• 13 Adelstein SJ, Green AJ, Howell RW. et al. Absorbed-dose specification in nuclear medicine. Journal of the ICRU 2002; 2: 1-110
• 14 Kletting P, Thieme A, Eberhardt N. et al. Modeling and Predicting Tumor Response in Radioligand Therapy. J Nucl Med 2019; 60: 65-70
• 15 Krauss M, Tappe K, Schuppert A. et al. Bayesian Population Physiologically-Based Pharmacokinetic (PBPK) Approach for a Physiologically Realistic Characterization of Interindividual Variability in Clinically Relevant Populations. PLoS ONE 2015; 10: e0139423
• 16 Wang G, Kalra M, Orton CG. Machine learning will transform radiology significantly within the next 5 years. Med Phys 2017; 44: 2041-2044
• 17 El Naqa I, Ruan D, Valdes G. et al. Machine learning and modeling: Data, validation, communication challenges. Med Phys 2018; 45: e834-e840
• 18 Maier A, Syben C, Lasser T. et al. A gentle introduction to deep learning in medical image processing. Z Med Phys 2019; 29: 86-101
• 19 Sahiner B, Pezeshk A, Hadjiiski LM. et al. Deep learning in medical imaging and radiation therapy. Med Phys 2019; 46: e1-e36
• 20 Uribe CF, Mathotaarachchi S, Gaudet V. et al. Machine Learning in Nuclear Medicine: Part 1—Introduction. Journal of Nuclear Medicine 2019; 60: 451-458
• 21 Siegel JA, Thomas SR, Stubbs JB. et al. MIRD pamphlet No. 16: Techniques for quantitative radiopharmaceutical biodistribution data acquisition and analysis for use in human radiation dose estimates. J Nucl Med 1999; 40: 37S-61S
• 22 Gaze MN, Chang Y-C, Flux GD. et al. Feasibility of Dosimetry-Based High-Dose ¹³¹I-Meta-Iodobenzylguanidine with Topotecan as a Radiosensitizer in Children with Metastatic Neuroblastoma. Cancer Biother Radiopharm 2005; 20: 195-199
• 23 Lassmann M, Chiesa C, Flux G. et al. EANM Dosimetry Committee guidance document: good practice of clinical dosimetry reporting. Eur J Nucl Med Mol Imaging 2011; 38: 192-200
• 24 Lassmann M, Glatting G. Dosimetrie für die Nuklearmedizinische Therapie. Der Nuklearmediziner 2018; 41: 11-12
• 25 Konijnenberg M. From imaging to dosimetry and biological effects. Q J Nucl Med Mol Imaging 2011; 55: 44-56
• 26 Gong K, Guan J, Kim K. et al. Iterative PET Image Reconstruction Using Convolutional Neural Network Representation. IEEE Transactions on Medical Imaging 2019; 38: 675-685
• 27 Hwang D, Kim KY, Kang SK. et al. Improving the Accuracy of Simultaneously Reconstructed Activity and Attenuation Maps Using Deep Learning. J Nucl Med 2018; 59: 1624-1629
• 28 Gong K, Guan J, Liu C. et al. PET Image Denoising Using a Deep Neural Network Through Fine Tuning. IEEE Transactions on Radiation and Plasma Medical Sciences 2019; 3: 153-161
• 29 Abualhaj B, Weng G, Ong M. et al. Comparison of five cluster validity indices performance in brain [¹⁸F]FET-PET image segmentation using k-means. Med Phys 2017; 44: 209-220
• 30 Jackson P, Hardcastle N, Dawe N. et al. Deep Learning Renal Segmentation for Fully Automated Radiation Dose Estimation in Unsealed Source Therapy. Front Oncol 2018; 8: 215
• 31 Wang HZZ, Li Y, Chen Z. et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from ¹⁸F-FDG PET/CT images. EJNMMI Res 2017; 7: 11
• 32 Blanc-Durand P, Van Der Gucht A, Schaefer N. et al. Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study. PLOS ONE 2018; 13: e0195798
• 33 Sauter AW, Mader KS, Sommer G. et al. Machine Learning for Improved PET/CT Fusion Images ECR-Congress. 2017. C-1776
• 34 Kletting P, Glatting G. Pharmakokinetische Modellierung in der Nuklearmedizin. Der Nuklearmediziner 2018; 41: 52-60
• 35 Strand SE, Zanzonico P, Johnson TK. Pharmacokinetic modeling. Med Phys 1993; 20: 515-527
• 36 Nestorov I. Whole body pharmacokinetic models. Clin Pharmacokinet 2003; 42: 883-908
• 37 Shah DK, Betts AM. Towards a platform PBPK model to characterize the plasma and tissue disposition of monoclonal antibodies in preclinical species and human. J Pharmacokinet Pharmacodyn 2011; 39: 67-86
• 38 Kletting P, Schuchardt C, Kulkarni HR. et al. Investigating the Effect of Ligand Amount and Injected Therapeutic Activity: A Simulation Study for ¹⁷⁷Lu-Labeled PSMA-Targeting Peptides. PLoS ONE 2016; 11: e0162303
• 39 Hardiansyah D, Maass C, Attarwala A. et al. The role of patient-based treatment planning in peptide receptor radionuclide therapy. Eur J Nucl Med Mol Imaging 2016; 43: 871-880
• 40 Kletting P, Müller B, Erentok B. et al. Differences in predicted and actually absorbed doses in peptide receptor radionuclide therapy. Med Phys 2012; 39: 5708-5717
• 41 Kletting P, Kull T, Bunjes D. et al. Radioimmunotherapy with anti-CD66 antibody: Improving the biodistribution using a physiologically based pharmacokinetic model. J Nucl Med 2010; 51: 484-491
• 42 Kletting P, Bunjes D, Reske SN. et al. Improving anti-CD45 antibody radioimmunotherapy using a physiologically based pharmacokinetic model. J Nucl Med 2009; 50: 296-302
• 43 Kletting P, Schimmel S, Kestler HA. et al. Molecular radiotherapy: The NUKFIT software for calculating the time-integrated activity coefficient. Med Phys 2013; 40: 102504
• 44 Muzic Jr RF, Christian BT. Evaluation of objective functions for estimation of kinetic parameters. Med Phys 2006; 33: 342-353
• 45 Leyun P, Caixia C, Uwe H. et al. Machine learning-based kinetic modeling: a robust and reproducible solution for quantitative analysis of dynamic PET data. Phys Med Biol 2017; 62: 3566
• 46 Mínguez P, Gustafsson J, Flux G. et al. Biologically effective dose in fractionated molecular radiotherapy—application to treatment of neuroblastoma with ¹³¹I-mIBG. Phys Med Biol 2016; 61: 2532
• 47 Borchiellini D, Etienne-Grimaldi M-C, Thariat J. et al. The impact of pharmacogenetics on radiation therapy outcome in cancer patients. A focus on DNA damage response genes. Cancer Treatment Reviews 2012; 38: 737-759
• 48 West CM, Barnett GC. Genetics and genomics of radiotherapy toxicity: towards prediction. Genome Med 2011; 3: 52
• 49 Aneesh TP, Sonal SM, Jose A. et al. Pharmacogenomics: the right drug to the right person. J Clin Med Res 2009; 1: 191-194
• 50 ICRP. Adult Reference Computational Phantoms. ICRP Publication 110. Ann ICRP. 2009: 39
• 51 Stabin MG, Emmons MA, Segars WP. et al. Realistic reference adult and paediatric phantom series for internal and external dosimetry. Radiat Prot Dosimetry 2012; 149: 56-59
• 52 Kost SD, Dewaraja YK, Abramson RG. et al. VIDA: A Voxel-Based Dosimetry Method for Targeted Radionuclide Therapy Using Geant4. Cancer Biother Radiopharm 2015; 30: 16-26
• 53 Lee MS, Kim JH, Paeng JC. et al. Whole-Body Voxel-Based Personalized Dosimetry: The Multiple Voxel S-Value Approach for Heterogeneous Media with Nonuniform Activity Distributions. Journal of Nuclear Medicine 2018; 59: 1133-1139
• 54 Valentin J. Basic anatomical and physiological data for use in radiological protection: reference values. A report of age- and gender-related differences in the anatomical and physiological characteristics of reference individuals. ICRP Publication 89. Ann ICRP 2002; 32: 5-265
• 55 Melodia L. Deep Learning Estimation of Absorbed Dose for Nuclear Medicine Diagnostics. 03.06.2018 (v3): Retrieved May 29, 2019, from the arXiv database
• 56 Grudzinski JJ, Tomé W, Weichert JP. et al. The biological effectiveness of targeted radionuclide therapy based on a whole-body pharmacokinetic model. Phys Med Biol 2010; 55: 5723-5734
• 57 O'Donoghue JA. Implications of nonuniform tumor doses for radioimmunotherapy. J Nucl Med 1999; 40: 1337-1341
• 58 Hillen T, de Vries G, Gong J. et al. From cell population models to tumor control probability: Including cell cycle effects. Acta Oncologica 2010; 49: 1315-1323
• 59 Marks LB, Yorke ED, Jackson A. et al. Use of normal tissue complication probability models in the clinic. Int J Radiat Oncol Biol Phys 2010; 76: S10-19
• 60 Dean JA, Wong KH, Welsh LC. et al. Normal tissue complication probability (NTCP) modelling using spatial dose metrics and machine learning methods for severe acute oral mucositis resulting from head and neck radiotherapy. Radiother Oncol 2016; 120: 21-27
• 61 Gabryś HS, Buettner F, Sterzing F. et al. Design and Selection of Machine Learning Methods Using Radiomics and Dosiomics for Normal Tissue Complication Probability Modeling of Xerostomia. Front Oncol 2018; 8: 35
• 62 Klement RJ, Allgäuer M, Appold S. et al. Support Vector Machine-Based Prediction of Local Tumor Control After Stereotactic Body Radiation Therapy for Early-Stage Non-Small Cell Lung Cancer. International journal of radiation oncology, biology, physics 2014; 88: 732-738
• 63 Gulliford SL, Webb S, Rowbottom CG. et al. Use of artificial neural networks to predict biological outcomes for patients receiving radical radiotherapy of the prostate. Radiotherapy and Oncology 2004; 71: 3-12
• 64 Lysenko A, Sharma A, Boroevich KA. et al. An integrative machine learning approach for prediction of toxicity-related drug safety. Life Sci Alliance 2018; 1: e201800098
• 65 Plisson F, Piggott AM. Predicting Blood–Brain Barrier Permeability of Marine-Derived Kinase Inhibitors Using Ensemble Classifiers Reveals Potential Hits for Neurodegenerative Disorders. Marine Drugs 2019; 17: 81
• 66 Chiu SH, Xie L. Toward High-Throughput Predictive Modeling of Protein Binding/Unbinding Kinetics. Journal of Chemical Information and Modeling 2016; 56: 1164-1174
• 67 Kumar V, Agrawal P, Kumar R. et al. Prediction of Cell-Penetrating Potential of Modified Peptides Containing Natural and Chemically Modified Residues. Front Microbiol 2018; 9: 725
• 68 Costello Z, Martin HG. A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data. NPJ Syst Biol Appl 2018; 4: 19
• 69 Lovinfosse P, Polus M, Van Daele D. et al. FDG PET/CT radiomics for predicting the outcome of locally advanced rectal cancer. Eur J Nucl Med Mol Imag 2018; 45: 365-375
• 70 Lucia F, Visvikis D, Desseroit M-C. et al. Prediction of outcome using pretreatment ¹⁸F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy. Eur J Nucl Med Mol Imag 2018; 45: 768-786
• 71 Abdollahi H, Mofid B, Shiri I. et al. Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer. Radiol Med 2019; 24: 555-567
• 72 Schumann S, Lassmann M, Eberlein U. Biodosimetrie in der Nuklearmedizin. Nuklearmediziner 2018; 41: 95-101
• 73 Forsting M. Machine Learning Will Change Medicine. J Nuc Med 2017; 58: 357-358
• 74 Lassmann M, Nosske D. Dosimetry of ²²³Ra-chloride: dose to normal organs and tissues. Eur J Nucl Med Mol Imag 2013; 40: 207-212
• 75 Stokke C, Gabiña PM, Solný P. et al. Dosimetry-based treatment planning for molecular radiotherapy: a summary of the 2017 report from the Internal Dosimetry Task Force. EJNMMI Phys 2017; 4: 27
• 76 Fan J, Wang J, Chen Z. et al. Automatic treatment planning based on three-dimensional dose distribution predicted from deep learning technique. Med Phys 2019; 46: 370-381
• 77 Tseng H-H, Luo Y, Ten Haken RK. et al. The Role of Machine Learning in Knowledge-Based Response-Adapted Radiotherapy. Front Oncol 2018; 8: 266
• 78 Weidlich V, Weidlich GA. Artificial Intelligence in Medicine and Radiation Oncology. Cureus 2018; 10: e2475