On the Use of Artificial Intelligence for Dosimetry of Radiopharmaceutical Therapies

Julia Franziska Brosch-Lenz; Astrid Delker; Fabian Schmidt; Johannes Tran-Gia

doi:10.1055/a-2179-6872

Nuklearmedizin - NuclearMedicine, Table of Contents

Nuklearmedizin 2023; 62(06): 379-388
DOI: 10.1055/a-2179-6872

Review

On the Use of Artificial Intelligence for Dosimetry of Radiopharmaceutical Therapies

Über die Verwendung von künstlicher Intelligenz für die Dosimetrie radiopharmazeutischer Therapien

Julia Franziska Brosch-Lenz‡

¹Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany (Ringgold ID: RIN27190)

,

Astrid Delker‡

²Department of Nuclear Medicine, LMU University Hospital, Munich, Germany

,

Fabian Schmidt‡

³Department of Nuclear Medicine and Clinical Molecular Imaging, University Hospital Tuebingen, Tuebingen, Germany

⁴Department of Preclinical Imaging and Radiopharmacy, Werner Siemens Imaging Center, Tuebingen, Germany (Ringgold ID: RIN505890)

,

Johannes Tran-Gia‡

⁵Department of Nuclear Medicine, University Hospital Wuerzburg, Wuerzburg, Germany (Ringgold ID: RIN27207)

› Author Affiliations

Abstract

Routine clinical dosimetry along with radiopharmaceutical therapies is key for future treatment personalization. However, dosimetry is considered complex and time-consuming with various challenges amongst the required steps within the dosimetry workflow. The general workflow for image-based dosimetry consists of quantitative imaging, the segmentation of organs and tumors, fitting of the time-activity-curves, and the conversion to absorbed dose. This work reviews the potential and advantages of the use of artificial intelligence to improve speed and accuracy of every single step of the dosimetry workflow.

Zusammenfassung

Routinemäßige klinische Dosimetrie ist unabdingbar für die zukünftige Personalisierung von radiopharmazeutischen Therapien. Allgemein wird die Dosimetrie jedoch als komplex und zeitaufwendig betrachtet, und die erforderlichen Schritte innerhalb des Dosimetrie-Workflows sind mit verschiedenen Herausforderungen verbunden. Der allgemeine Workflow für die bildbasierte Dosimetrie besteht aus der quantitativen Bildgebung, der Segmentierung von Organen und Tumoren, dem Modellieren der Zeit-Aktivitäts-Kurven und der Umrechnung in die absorbierte Dosis. In dieser Arbeit werden das Potenzial und die Vorteile des Einsatzes von künstlicher Intelligenz zur Verbesserung der Geschwindigkeit und Genauigkeit jedes einzelnen Schrittes des Dosimetrie-Workflows untersucht.

Keywords

Dosimetry - Artificial Intelligence - Radiopharmaceutical Therapies

Full Text

References

References
1 Sartor O, De Bono J, Chi KN. et al. Lutetium-177–PSMA-617 for metastatic castration-resistant prostate cancer. New England Journal of Medicine 2021; 385 (12) 1091-1103
2 Ferlay J, Colombet M, Soerjomataram I. et al. Cancer statistics for the year 2020: An overview. International journal of cancer 2021; 149 (04) 778-789
3 Strigari L, Konijnenberg M, Chiesa C. et al. The evidence base for the use of internal dosimetry in the clinical practice of molecular radiotherapy. European journal of nuclear medicine and molecular imaging 2014; 41: 1976-1988
4 Ilan E, Sandström M, Wassberg C. et al. Dose response of pancreatic neuroendocrine tumors treated with peptide receptor radionuclide therapy using 177Lu-DOTATATE. Journal of nuclear medicine 2015; 56 (02) 177-82
5 Garin E, Tselikas L, Guiu B. et al. Personalised versus standard dosimetry approach of selective internal radiation therapy in patients with locally advanced hepatocellular carcinoma (DOSISPHERE-01): a randomised, multicentre, open-label phase 2 trial. The lancet Gastroenterology & hepatology 2021; 6 (01) 17-29
6 Garske-Román U, Sandström M, Fröss Baron K. et al. Prospective observational study of 177 Lu-DOTA-octreotate therapy in 200 patients with advanced metastasized neuroendocrine tumours (NETs): feasibility and impact of a dosimetry-guided study protocol on outcome and toxicity. European journal of nuclear medicine and molecular imaging 2018; 45: 970-988
7 Cremonesi M, Ferrari ME, Bodei L. et al. Correlation of dose with toxicity and tumour response to 90 Y-and 177 Lu-PRRT provides the basis for optimization through individualized treatment planning. European journal of nuclear medicine and molecular imaging 2018; 45: 2426-2441
8 Zaknun JJ, Bodei L, Mueller-Brand J. et al. The joint IAEA, EANM, and SNMMI practical guidance on peptide receptor radionuclide therapy (PRRNT) in neuroendocrine tumours. European journal of nuclear medicine and molecular imaging 2013; 40 (05) 800-816
9 Kratochwil C, Fendler WP, Eiber M. et al. EANM procedure guidelines for radionuclide therapy with 177 Lu-labelled PSMA-ligands (177 Lu-PSMA-RLT). European journal of nuclear medicine and molecular imaging 2019; 46: 2536-2544
10 Gafita A, Wang H, Robertson A. et al. Tumor sink effect in 68Ga-PSMA-11 PET: myth or reality?. Journal of Nuclear Medicine 2022; 63 (02) 226-232
11 Konijnenberg M, Herrmann K, Kobe C. et al. EANM position paper on article 56 of the Council Directive 2013/59/Euratom (basic safety standards) for nuclear medicine therapy. European journal of nuclear medicine and molecular imaging 2021; 48: 67-72
12 Bolch WE, Eckerman KF, Sgouros G. et al. MIRD pamphlet no. 21: a generalized schema for radiopharmaceutical dosimetry—standardization of nomenclature. Journal of Nuclear Medicine 2009; 50 (03) 477-484
13 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. Journal of Nuclear Medicine 1999; 40 (02) 37S-61S
14 Arabi H, Zaidi H. Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy. European Journal of Hybrid Imaging 2020; 4 (01) 1-23
15 Liberini V, Laudicella R, Balma M. et al. Radiomics and artificial intelligence in prostate cancer: new tools for molecular hybrid imaging and theragnostics. European Radiology Experimental 2022; 6 (01) 27
16 Milan D, Jens M, Stefaan V. Artificial intelligence with deep learning in nuclear medicine and radiology. EJNMMI Physics 2021;8(01).
17 Mora-Ramirez E, Santoro L, Cassol E. et al. Comparison of commercial dosimetric software platforms in patients treated with 177Lu-DOTATATE for peptide receptor radionuclide therapy. Medical Physics 2020; 47 (09) 4602-4615
18 Gear J, Stokke C, Terwinghe C. et al. EANM enabling guide: how to improve the accessibility of clinical dosimetry. European Journal of Nuclear Medicine and Molecular Imaging 2023; 50 (07) 1861-1868
19 Schwenck J, Sonanini D, Cotton JM. et al. Advances in PET imaging of cancer. Nature Reviews Cancer 2023; 1-17
20 Fendler WP, Pabst KM, Kessler L. et al. Safety and efficacy of 90Y-FAPI-46 radioligand therapy in patients with advanced sarcoma and other cancer entities. Clinical Cancer Research 2022; 28 (19) 4346-4353
21 Fiedler L, Kellner M, Gosewisch A. et al. Evaluation of 177Lu [Lu]-CHX-A ″-DTPA-6A10 Fab as a radioimmunotherapy agent targeting carbonic anhydrase XII. Nuclear medicine and biology 2018; 60: 55-62
22 Pooja D, Gunukula A, Gupta N. et al. Bombesin receptors as potential targets for anticancer drug delivery and imaging. The international journal of biochemistry & cell biology 2019; 114: 105567
23 Grob NM, Schibli R, Béhé M. et al. Improved tumor-targeting with peptidomimetic analogs of minigastrin 177Lu-PP-F11N. Cancers 2021; 13 (11) 2629
24 Wickstroem K, Karlsson J, Ellingsen C. et al. Synergistic effect of a HER2 targeted thorium-227 conjugate in combination with olaparib in a BRCA2 deficient xenograft model. Pharmaceuticals 2019; 12 (04) 155
25 Sundar LKS, Lassen ML, Gutschmayer S. et al. Fully Automated, Fast Motion Correction of Dynamic Whole-Body and Total-Body PET/CT Imaging Studies. Journal of Nuclear Medicine. 2023
26 Ritt P. Recent developments in SPECT/CT. Seminars in Nuclear Medicine 2022; 52 (03) 276-285
27 Sarrut D, Bardiès 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. Medical physics 2014; 41 (06) 064301
28 Bolch WE, Bouchet LG, Robertson JS. et al. MIRD pamphlet no. 17: the dosimetry of nonuniform activity distributions—radionuclide S values at the voxel level. Journal of Nuclear Medicine 1999; 40 (01) 11S-36S
29 Kratochwil C, Fendler WP, Eiber M. et al. EANM procedure guidelines for radionuclide therapy with 177 Lu-labelled PSMA-ligands (177 Lu-PSMA-RLT). European journal of nuclear medicine and molecular imaging 2019; 46 (12) 2536-2544
30 Ljungberg M, Celler A, Konijnenberg MW. et al. MIRD pamphlet no. 26: joint EANM/MIRD guidelines for quantitative 177Lu SPECT applied for dosimetry of radiopharmaceutical therapy. Journal of nuclear medicine 2016; 57 (01) 151-162
31 Tran-Gia J, Denis-Bacelar AM, Ferreira KM. et al. A multicentre and multi-national evaluation of the accuracy of quantitative Lu-177 SPECT/CT imaging performed within the MRTDosimetry project. EJNMMI physics 2021; 8: 1-17
32 Gosewisch A, Ilhan H, Tattenberg S. et al. 3D Monte Carlo bone marrow dosimetry for Lu-177-PSMA therapy with guidance of non-invasive 3D localization of active bone marrow via Tc-99m-anti-granulocyte antibody SPECT/CT. EJNMMI research 2019; 9 (01) 76
33 Rydén T, Van Essen M, Marin I. et al. Deep-Learning Generation of Synthetic Intermediate Projections Improves 177Lu SPECT Images Reconstructed with Sparsely Acquired Projections. Journal of Nuclear Medicine 2021; 62 (04) 528-535
34 Leube J, Gustafsson J, Lassmann M. et al. Analysis of a deep learning-based method for generation of SPECT projections based on a large Monte Carlo simulated dataset. EJNMMI physics 2022; 9 (01) 1-20
35 Minarik D, Enqvist O, Trägårdh E. Denoising of scintillation camera images using a deep convolutional neural network: a Monte Carlo simulation approach. Journal of Nuclear Medicine 2020; 61 (02) 298-303
36 Sohlberg A, Kangasmaa T, Constable C. et al. Comparison of deep learning-based denoising methods in cardiac SPECT. EJNMMI physics 2023; 10 (01) 9
37 Liu J, Yang Y, Wernick MN. et al. Deep learning with noise-to-noise training for denoising in SPECT myocardial perfusion imaging. Medical physics 2021; 48 (01) 156-168
38 Bonardel G, Dupont A, Decazes P. et al. Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition. EJNMMI physics 2022; 9 (01) 36
39 Wang Y, Yu B, Wang L. et al. 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. Neuroimage 2018; 174: 550-562
40 Sari H, Teimoorisichani M, Mingels C. et al. Quantitative evaluation of a deep learning-based framework to generate whole-body attenuation maps using LSO background radiation in long axial FOV PET scanners. European journal of nuclear medicine and molecular imaging 2022; 49 (13) 4490-4502
41 Shanbhag AD, Miller RJ, Pieszko K. et al. Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT. Journal of Nuclear Medicine 2023; 64 (03) 472-478
42 Xiang H, Lim H, Fessler JA. et al. A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions. European journal of nuclear medicine and molecular imaging 2020; 1-12
43 Shao W, Pomper MG, Du Y. A learned reconstruction network for SPECT imaging. IEEE transactions on radiation and plasma medical sciences 2020; 5 (01) 26-34
44 Dietze MM, Branderhorst W, Kunnen B. et al. Accelerated SPECT image reconstruction with FBP and an image enhancement convolutional neural network. EJNMMI physics 2019; 6 (01) 1-12
45 Häggström I, Schmidtlein CR, Campanella G. et al. DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problem. Medical image analysis 2019; 54: 253-262
46 Xie H, Liu Z, Shi L. et al. Segmentation-free partial volume correction for cardiac SPECT using deep learning. Soc Nuclear Med. 2022
47 Li T, Zhang M, Qi W. et al. Motion correction of respiratory-gated PET images using deep learning based image registration framework. Physics in Medicine & Biology 2020; 65 (15) 155003
48 Li Z, Fessler JA, Mikell JK. et al. DblurDoseNet: A deep residual learning network for voxel radionuclide dosimetry compensating for single-photon emission computerized tomography imaging resolution. Medical physics 2022; 49 (02) 1216-1230
49 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 (07) 1133-1139
50 Akhavanallaf A, Shiri I, Arabi H. et al. Whole-body voxel-based internal dosimetry using deep learning. European Journal of Nuclear Medicine and Molecular Imaging 2021; 48 (03) 670-682
51 Vinod SK, Jameson MG, Min M. et al. Uncertainties in volume delineation in radiation oncology: a systematic review and recommendations for future studies. Radiotherapy and Oncology 2016; 121 (02) 169-179
52 Starmans MP, van der Voort SR, Tovar JMC. et al. Radiomics: data mining using quantitative medical image features. Handbook of Medical Image Computing and Computer Assisted Intervention. In: . Elsevier; 2020: 429-456
53 Gudi S, Ghosh-Laskar S, Agarwal JP. et al. Interobserver variability in the delineation of gross tumour volume and specified organs-at-risk during IMRT for head and neck cancers and the impact of FDG-PET/CT on such variability at the primary site. Journal of medical imaging and radiation sciences 2017; 48 (02) 184-192
54 Bieth M, Peter L, Nekolla SG. et al. Segmentation of skeleton and organs in whole-body CT images via iterative trilateration. IEEE transactions on medical imaging 2017; 36 (11) 2276-2286
55 Yu Y, Decazes P, Gardin I. et al. 3D lymphoma segmentation in PET/CT images based on fully connected CRFs. Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment. In: . Springer; 2017: 3-12
56 Xu L, Tetteh G, Lipkova J. et al. Automated whole-body bone lesion detection for multiple myeloma on 68 Ga-Pentixafor PET/CT imaging using deep learning methods. Contrast media & molecular imaging 2018; 2018
57 Wang H, Zhang N, Huo L. et al. Dual-modality multi-atlas segmentation of torso organs from [18 F] FDG-PET/CT images. International journal of computer assisted radiology and surgery 2019; 14 (03) 473-482
58 Dou Q, Ouyang C, Chen C. et al. Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. arXiv preprint arXiv:180410916. 2018
59 Jackson P, Hardcastle N, Dawe N. et al. Deep learning renal segmentation for fully automated radiation dose estimation in unsealed source therapy. Frontiers in oncology 2018; 8: 215
60 Ryden T, van Essen M, Svensson J. et al. Deep learning-based SPECT/CT quantification of 177Lu uptake in the kidneys. Soc Nuclear Med. 2020
61 Tang X, Jafargholi Rangraz E, Coudyzer W. et al. Whole liver segmentation based on deep learning and manual adjustment for clinical use in SIRT. European journal of nuclear medicine and molecular imaging 2020; 47: 2742-2752
62 Kletting P, Schimmel S, Kestler H. et al. Molecular radiotherapy: the NUKFIT software for calculating the time-integrated activity coefficient. Medical physics 2013; 40 (10) 102504
63 Sarrut D, Halty A, Badel JN. et al. Voxel-based multimodel fitting method for modeling time activity curves in SPECT images. Medical physics 2017; 44 (12) 6280-6288
64 Götz TI, Schmidkonz C, Chen S. et al. A deep learning approach to radiation dose estimation. Physics in Medicine & Biology 2020; 65 (03) 035007
65 Scarinci I, Valente M, Pérez P. A machine learning-based model for a dose point kernel calculation. EJNMMI physics 2023; 10 (01) 1-18
66 Lee MS, Hwang D, Kim JH. et al. Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry. Scientific reports 2019; 9 (01) 1-9
67 Kim KM, Lee MS, Suh MS. et al. Voxel-Based Internal Dosimetry for 177Lu-Labeled Radiopharmaceutical Therapy Using Deep Residual Learning. Nuclear Medicine and Molecular Imaging 2023; 57 (02) 94-102
68 Xue S, Gafita A, Dong C. et al. Application of machine learning to pretherapeutically estimate dosimetry in men with advanced prostate cancer treated with 177Lu-PSMA I&T therapy. European journal of nuclear medicine and molecular imaging 2022; 49 (12) 4064-4072
69 Hernandez-Boussard T, Macklin P, Greenspan EJ. et al. Digital twins for predictive oncology will be a paradigm shift for precision cancer care. Nature medicine 2021; 27 (12) 2065-2066
70 Brosch-Lenz J, Uribe C, Rahmim A. et al. Theranostic Digital Twins: An indispensable prerequisite for personalized cancer care. J Nucl Med 2023; 64 (03) 501
71 Rahmim A, Brosch-Lenz J, Fele-Paranj A. et al. Theranostic digital twins for personalized radiopharmaceutical therapies: Reimagining theranostics via computational nuclear oncology. Frontiers in oncology 2022; 12: 1062592