Top

European Journal of Nuclear Medicine and Molecular Imaging

Published in:

Open Access 01-03-2021 | Original Article

Whole-body voxel-based internal dosimetry using deep learning

Authors: Azadeh Akhavanallaf, Iscaac Shiri, Hossein Arabi, Habib Zaidi

Published in: European Journal of Nuclear Medicine and Molecular Imaging | Issue 3/2021

Abstract

Purpose

In the era of precision medicine, patient-specific dose calculation using Monte Carlo (MC) simulations is deemed the gold standard technique for risk-benefit analysis of radiation hazards and correlation with patient outcome. Hence, we propose a novel method to perform whole-body personalized organ-level dosimetry taking into account the heterogeneity of activity distribution, non-uniformity of surrounding medium, and patient-specific anatomy using deep learning algorithms.

Methods

We extended the voxel-scale MIRD approach from single S-value kernel to specific S-value kernels corresponding to patient-specific anatomy to construct 3D dose maps using hybrid emission/transmission image sets. In this context, we employed a Deep Neural Network (DNN) to predict the distribution of deposited energy, representing specific S-values, from a single source in the center of a 3D kernel composed of human body geometry. The training dataset consists of density maps obtained from CT images and the reference voxelwise S-values generated using Monte Carlo simulations. Accordingly, specific S-value kernels are inferred from the trained model and whole-body dose maps constructed in a manner analogous to the voxel-based MIRD formalism, i.e., convolving specific voxel S-values with the activity map. The dose map predicted using the DNN was compared with the reference generated using MC simulations and two MIRD-based methods, including Single and Multiple S-Values (SSV and MSV) and Olinda/EXM software package.

Results

The predicted specific voxel S-value kernels exhibited good agreement with the MC-based kernels serving as reference with a mean relative absolute error (MRAE) of 4.5 ± 1.8 (%). Bland and Altman analysis showed the lowest dose bias (2.6%) and smallest variance (CI: − 6.6, + 1.3) for DNN. The MRAE of estimated absorbed dose between DNN, MSV, and SSV with respect to the MC simulation reference were 2.6%, 3%, and 49%, respectively. In organ-level dosimetry, the MRAE between the proposed method and MSV, SSV, and Olinda/EXM were 5.1%, 21.8%, and 23.5%, respectively.

Conclusion

The proposed DNN-based WB internal dosimetry exhibited comparable performance to the direct Monte Carlo approach while overcoming the limitations of conventional dosimetry techniques in nuclear medicine.

Baumann M, Krause M, Overgaard J, Debus J, Bentzen SM, Daartz J, et al. Radiation oncology in the era of precision medicine. Nat Rev Cancer. 2016;16:234–49.PubMedCrossRef

Stabin MG, Madsen MT, Zaidi H. Personalized dosimetry is a must for appropriate molecular radiotherapy. Med Phys. 2019;46:4713–6. https://doi.org/10.1002/mp.13820.PubMedCrossRef

Zaidi H, Xu XG. Computational anthropomorphic models of the human anatomy: the path to realistic Monte Carlo modeling in radiological sciences. Annu Rev Biomed Eng. 2007;9:471–500.PubMedCrossRef

Bolch WE, Bouchet LG, Robertson JS, Wessels BW, Siegel JA, Howell RW, et al. MIRD pamphlet No. 17: the dosimetry of nonuniform activity distributions-radionuclide S values at the voxel level. Medical Internal Radiation Dose Committee. J Nucl Med. 1999;40:11S–36S.PubMed

Johnson PB, Whalen SR, Wayson M, Juneja B, Lee C, Bolch WE. Hybrid patient-dependent phantoms covering statistical distributions of body morphometry in the US adult and pediatric population. Proc IEEE. 2009;97:2060–75.CrossRef

Akhavanallaf A, Xie T, Zaidi H. Development of a library of adult computational phantoms based on anthropometric indexes. IEEE Trans Radiat Plasma Med Sci. 2019;3:65–75.CrossRef

Na YH, Zhang B, Zhang J, Caracappa PF, Xu XG. Deformable adult human phantoms for radiation protection dosimetry: anthropometric data representing size distributions of adult worker populations and software algorithms. Phys Med Biol. 2010;55:3789–811.PubMedPubMedCentralCrossRef

Xie T, Akhavanallaf A, Zaidi H. Construction of patient-specific computational models for organ dose estimation in radiological imaging. Med Phys. 2019;46:2403–11. https://doi.org/10.1002/mp.13471.PubMedCrossRef

Xie T, Zaidi H. Estimation of the radiation dose in pregnancy: an automated patient-specific model using convolutional neural networks. Eur Radiol. 2019;29:6805–15. https://doi.org/10.1007/s00330-019-06296-4.PubMedCrossRef

10.

Berger MJ. Distribution of absorbed dose around point sources of electrons and beta particles in water and other media. Washington, DC: National Bureau of Standards; 1971.

11.

Kolbert KS, Sgouros G, Scott AM, Bronstein JE, Malane RA, Zhang J, et al. Implementation and evaluation of patient-specific three-dimensional internal dosimetry. J Nucl Med. 1997;38:301–8.PubMed

12.

Giap HB, Macey DJ, Bayouth JE, Boyer AL. Validation of a dose-point kernel convolution technique for internal dosimetry. Phys Med Biol. 1995;40:365–81. https://doi.org/10.1088/0031-9155/40/3/003.PubMedCrossRef

13.

Zaidi H. Relevance of accurate Monte Carlo modeling in nuclear medical imaging. Med Phys. 1999;26:574–608. https://doi.org/10.1118/1.598559.PubMedCrossRef

14.

Gardin I, Bouchet LG, Assie K, Caron J, Lisbona A, Ferrer L, et al. Voxeldose: a computer program for 3-D dose calculation in therapeutic nuclear medicine. Cancer Biother Radiopharm. 2003;18:109–15. https://doi.org/10.1089/108497803321269386.PubMedCrossRef

15.

Papadimitroulas P, Loudos G, Nikiforidis GC, Kagadis GC. A dose point kernel database using GATE Monte Carlo simulation toolkit for nuclear medicine applications: comparison with other Monte Carlo codes. Med Phys. 2012;39:5238–47.PubMedCrossRef

16.

Besemer AE, Yang YM, Grudzinski JJ, Hall LT, Bednarz BP. Development and validation of RAPID: a patient-specific Monte Carlo three-dimensional internal dosimetry platform. Cancer Biother Radiopharm. 2018;33:155–65.PubMedPubMedCentralCrossRef

17.

Ljungberg M, Gleisner KS. 3-D image-based dosimetry in radionuclide therapy. IEEE Trans Radiat Plasma Med Sci. 2018;2:527–40.CrossRef

18.

Dieudonne A, Hobbs RF, Lebtahi R, Maurel F, Baechler S, Wahl RL, et al. Study of the impact of tissue density heterogeneities on 3-dimensional abdominal dosimetry: comparison between dose kernel convolution and direct Monte Carlo methods. J Nucl Med. 2013;54:236–43. https://doi.org/10.2967/jnumed.112.105825.PubMedCrossRef

19.

Loudos G, Tsougos I, Boukis S, Karakatsanis N, Georgoulias P, Theodorou K, et al. A radionuclide dosimetry toolkit based on material-specific Monte Carlo dose kernels. Nucl Med Commun. 2009;30:504–12. https://doi.org/10.1097/MNM.0b013e3283299a11.PubMedCrossRef

20.

Khazaee Moghadam M, Kamali Asl A, Geramifar P, Zaidi H. Evaluating the application of tissue-specific dose kernels instead of water dose kernels in internal dosimetry: a Monte Carlo study. Cancer Biother Radiopharm. 2016;31:367–79. https://doi.org/10.1089/cbr.2016.2117.PubMedCrossRef

21.

Lee MS, Kim JH, Paeng JC, Kang KW, Jeong JM, Lee DS, et al. Whole-body voxel-based personalized dosimetry: the multiple voxel S-value approach for heterogeneous media with nonuniform activity distributions. J Nucl Med. 2018;59:1133–9. https://doi.org/10.2967/jnumed.117.201095.PubMedCrossRef

22.

Shiri I, Arabi H, Geramifar P, Hajianfar G, Ghafarian P, Rahmim A, et al. Deep-JASC: joint attenuation and scatter correction in whole-body (18)F-FDG PET using a deep residual network. Eur J Nucl Med Mol Imaging. 2020, in press. https://doi.org/10.1007/s00259-020-04852-5.

23.

Xiang H, Lim H, Fessler JA, Dewaraja YK. A deep neural network for fast and accurate scatter estimation in quantitative SPECT/CT under challenging scatter conditions. Eur J Nucl Med Mol Imaging. 2020, in press. https://doi.org/10.1007/s00259-020-04840-9.

24.

Dong X, Lei Y, Wang T, Higgins K, Liu T, Curran WJ, et al. Deep learning-based attenuation correction in the absence of structural information for whole-body PET imaging. Phys Med Biol. 2020;65:055011. https://doi.org/10.1088/1361-6560/ab652c.PubMedPubMedCentralCrossRef

25.

Sanaat A, Arabi H, Mainta I, Garibotto V, Zaidi H. Projection-space implementation of deep learning-guided low-dose brain PET imaging improves performance over implementation in image-space. J Nucl Med. 2020, in press. https://doi.org/10.2967/jnumed.119.239327.

26.

Zaharchuk G. Next generation research applications for hybrid PET/MR and PET/CT imaging using deep learning. Eur J Nucl Med Mol Imaging. 2019;46:2700–7. https://doi.org/10.1007/s00259-019-04374-9.PubMedPubMedCentralCrossRef

27.

Shiri I, AmirMozafari Sabet K, Arabi H, Pourkeshavarz M, Teimourian B, Ay MR, et al. Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks. J Nucl Cardiol. 2020, in press. https://doi.org/10.1007/s12350-020-02119-y.

28.

Seo H, Badiei Khuzani M, Vasudevan V, Huang C, Ren H, Xiao R, et al. Machine learning techniques for biomedical image segmentation: an overview of technical aspects and introduction to state-of-art applications. Med Phys. 2020;47:e148–e67. https://doi.org/10.1002/mp.13649.PubMedCrossRef

29.

Mardani M, Dong P, Xing L. Deep-learning based prediction of achievable dose for personalizing inverse treatment planning. Int J Radiat Oncol Biol Phys. 2016;96:E419–E20.CrossRef

30.

Nguyen D, Long T, Jia X, Lu W, Gu X, Iqbal Z, et al. A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning. Sci Rep. 2019;9:1076. https://doi.org/10.1038/s41598-018-37741-x.PubMedPubMedCentralCrossRef

31.

Ma M, Buyyounouski MK, Vasudevan V, Xing L, Yang Y. Dose distribution prediction in isodose feature-preserving voxelization domain using deep convolutional neural network. Med Phys. 2019;46:2978–87. https://doi.org/10.1002/mp.13618.PubMedCrossRef

32.

Kearney V, Chan JW, Haaf S, Descovich M, Solberg TD. DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks. Phys Med Biol. 2018;63:235022.PubMedCrossRef

33.

Jarrett D, Stride E, Vallis K, Gooding MJ. Applications and limitations of machine learning in radiation oncology. Br J Radiol. 2019;92:20190001. https://doi.org/10.1259/bjr.20190001.PubMedPubMedCentralCrossRef

34.

Andreo P. Monte Carlo simulations in radiotherapy dosimetry. Radiat Oncol. 2018;13:121.PubMedPubMedCentralCrossRef

35.

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. 2019;9:10308.PubMedPubMedCentralCrossRef

36.

Götz TI, Schmidkonz C, Chen S, Al-Baddai S, Kuwert T, Lang E. A deep learning approach to radiation dose estimation. Phys Med Biol. 2020;65:035007.PubMedCrossRef

37.

Peng Z, Fang X, Yan P, Shan H, Liu T, Pei X, et al. A method of rapid quantification of patient-specific organ doses for CT using deep-learning-based multi-organ segmentation and GPU accelerated Monte Carlo dose computing. Med Phys. 2020;47:2526–36.PubMedCrossRef

38.

Karbalaee M, Shahbazi-Gahrouei D, Tavakoli MB. An approach in radiation therapy treatment planning: a fast, GPU-based Monte Carlo method. J Med Signals Sens. 2017;7:108–13.PubMedPubMedCentralCrossRef

39.

Jia X, Ziegenhein P, Jiang SB. GPU-based high-performance computing for radiation therapy. Phys Med Biol. 2014;59:R151–82. https://doi.org/10.1088/0031-9155/59/4/R151.PubMedPubMedCentralCrossRef

40.

Loevinger R, Pfalzner P, Eisenlohr H, Malo S, Sanielevici A, Nagl J. The IAEA program in medical radiation dosimetry. Ann N Y Acad Sci. 1969;161:158–67.PubMedCrossRef

41.

Cristy M. Applying the reciprocal dose principle to heterogeneous phantoms: practical experience from Monte Carlo studies. Phys Med Biol. 1983;28:1289–303.PubMedCrossRef

42.

Lee C, Lee C, Shah AP, Bolch WE. An assessment of bone marrow and bone endosteum dosimetry methods for photon sources. Phys Med Biol. 2006;51:5391–407.PubMedCrossRef

43.

Seuntjens J, Strydom W, Shortt K. Dosimetric principles, quantities and units. In: Podgorsak EB, editor. Radiation oncology physics: a handbook for teachers and students. Vienna: IAEA; 2005.

44.

Bailey DL, Karp JS, Surti S. Physics and instrumentation in PET. Positron emission tomography: Springer; 2005. p. 13–39.

45.

Li W, Wang G, Fidon L, Ourselin S, Cardoso MJ, Vercauteren T. On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. Int Conf Inf Process Med Imaging. 2017:348–60.

46.

Schneider W, Bortfeld T, Schlegel W. Correlation between CT numbers and tissue parameters needed for Monte Carlo simulations of clinical dose distributions. Phys Med Biol. 2000;45:459–78.PubMedCrossRef

47.

Waters LS. MCNPX user’s manual. Los Alamos Nat Lab. 2002.

48.

Jan S, Comtat C, Strul D, Santin G, Trebossen R. Monte Carlo simulation for the ECAT EXACT HR+ system using GATE. IEEE Trans Nucl Sci. 2005;52:627–33.CrossRef

49.

Zaker N, Kotasidis F, Garibotto V, Zaidi H. Assessment of lesion detectability in dynamic whole-body PET imaging using compartmental and Patlak parametric mapping. Clin Nucl Med. 2020;45:e221–e31.PubMedCrossRef

50.

Fahrni G, Karakatsanis N, Di Domenicantonio G, Garibotto V, Zaidi H. Does whole-body Patlak 18F-FDG PET imaging improve lesion detectability in clinical oncology? Eur Radiol. 2019;29:4812–21. https://doi.org/10.1007/s00330-018-5966-1.PubMedCrossRef

51.

Hubbell JH, Seltzer SM. Tables of X-ray mass attenuation coefficients and mass energy-absorption coefficients 1 keV to 20 MeV for elements Z= 1 to 92 and 48 additional substances of dosimetric interest. Gaithersburg: National Inst. of Standards and Technology-PL; 1995.CrossRef

52.

Stabin MG, Sparks RB, Crowe E. OLINDA/EXM: the second-generation personal computer software for internal dose assessment in nuclear medicine. J Nucl Med. 2005;46:1023–7.PubMed

53.

Chiesa C, Bardiès M, Zaidi H. Voxel-based dosimetry is superior to mean absorbed dose approach for establishing dose-effect relationship in targeted radionuclide therapy. Med Phys. 2019;46:5403–6.PubMedCrossRef

54.

Howard DM, Kearfott KJ, Wilderman SJ, Dewaraja YK. Comparison of I-131 radioimmunotherapy tumor dosimetry: unit density sphere model versus patient-specific Monte Carlo calculations. Cancer Biother Radiopharm. 2011;26:615–21.PubMedPubMedCentralCrossRef

55.

Divoli A, Chiavassa S, Ferrer L, Barbet J, Flux GD, Bardies M. Effect of patient morphology on dosimetric calculations for internal irradiation as assessed by comparisons of Monte Carlo versus conventional methodologies. J Nucl Med. 2009;50:316–23.PubMedCrossRef

Title: Whole-body voxel-based internal dosimetry using deep learning
Authors: Azadeh Akhavanallaf
Iscaac Shiri
Hossein Arabi
Habib Zaidi
Publication date: 01-03-2021
Publisher: Springer Berlin Heidelberg
Published in: European Journal of Nuclear Medicine and Molecular Imaging / Issue 3/2021
Print ISSN: 1619-7070
Electronic ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-020-05013-4

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Whole-body voxel-based internal dosimetry using deep learning

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 3/2021

[68 Ga]Ga-Prostate-Specific Membrane Antigen PET/CT: a novel method for imaging patients with hepatocellular carcinoma

Nucleophosmin 1 overexpression correlates with 18F-FDG PET/CT metabolic parameters and improves diagnostic accuracy in patients with lung adenocarcinoma

Reporter gene imaging “visualized” the integration of two growing technologies: CRISPR/Cas9-based genome editing and induced pluripotent stem cell therapy

A pheochromocytoma wrapped in an IgG4-related disease

Biodistribution and dosimetry of a single dose of albumin-binding ligand [177Lu]Lu-PSMA-ALB-56 in patients with mCRPC

Increased incidence of interstitial pneumonia detected on [18F]-FDG-PET/CT in asymptomatic cancer patients during COVID-19 pandemic in Lombardy: a casualty or COVID-19 infection?