A deep-learning-based prediction model for the biodistribution of
Deep Learning
Embolization, Therapeutic
Humans
Liver
/ diagnostic imaging
Liver Neoplasms
/ diagnostic imaging
Microspheres
Positron Emission Tomography Computed Tomography
Technetium Tc 99m Aggregated Albumin
Tissue Distribution
Tomography, Emission-Computed, Single-Photon
Yttrium Radioisotopes
/ therapeutic use
biodistribution prediction
deep learning
radioembolization
treatment planning
yttrium-90
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Nov 2021
Nov 2021
Historique:
revised:
24
09
2021
received:
08
04
2021
accepted:
27
09
2021
pubmed:
11
10
2021
medline:
18
11
2021
entrez:
10
10
2021
Statut:
ppublish
Résumé
Radioembolization with The purpose of the present study was to employ deep learning (DL) algorithms to differentiate patterns of pretreatment distribution of Data for 19 patients with liver cancer (10 with hepatocellular carcinoma, 5 with intrahepatic cholangiocarcinoma, 4 with liver metastases) who underwent radioembolization with The comparison of the real and predicted PET/CT scans showed an average absorbed dose difference of 5.42% ± 19.31% and 0.44% ± 1.64% for the tumor and the liver area, respectively. The average absorbed dose differences were 7.98 ± 31.39 Gy and 0.03 ± 0.25 Gy for the tumor and the non-tumor liver parenchyma, respectively. Our model had a general tendency to underpredict the dosimetric results; the largest differences were noticed in one case, where the model underestimated the dose to the tumor area by 56.75% or 72.82 Gy. The proposed deep-learning-based pretreatment planning method for liver radioembolization accurately predicted
Sections du résumé
BACKGROUND
BACKGROUND
Radioembolization with
PURPOSE
OBJECTIVE
The purpose of the present study was to employ deep learning (DL) algorithms to differentiate patterns of pretreatment distribution of
METHODS
METHODS
Data for 19 patients with liver cancer (10 with hepatocellular carcinoma, 5 with intrahepatic cholangiocarcinoma, 4 with liver metastases) who underwent radioembolization with
RESULTS
RESULTS
The comparison of the real and predicted PET/CT scans showed an average absorbed dose difference of 5.42% ± 19.31% and 0.44% ± 1.64% for the tumor and the liver area, respectively. The average absorbed dose differences were 7.98 ± 31.39 Gy and 0.03 ± 0.25 Gy for the tumor and the non-tumor liver parenchyma, respectively. Our model had a general tendency to underpredict the dosimetric results; the largest differences were noticed in one case, where the model underestimated the dose to the tumor area by 56.75% or 72.82 Gy.
CONCLUSIONS
CONCLUSIONS
The proposed deep-learning-based pretreatment planning method for liver radioembolization accurately predicted
Substances chimiques
Technetium Tc 99m Aggregated Albumin
0
Yttrium Radioisotopes
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7427-7438Subventions
Organisme : European Regional Development Fund
ID : T11EPA4-00055
Organisme : European Social Fund
ID : MIS-5000432
Organisme : European Social Fund
ID : MIS-5033021
Informations de copyright
© 2021 American Association of Physicists in Medicine.
Références
Bouvry C, Palard X, Edeline J, et al. Transarterial radioembolization (TARE) agents beyond (90)Y-microspheres. Biomed Res Int. 2018;2018:1435302.
Bastiaannet R, Kappadath SC, Kunnen B, Braat A, Lam M, de Jong H. The physics of radioembolization. EJNMMI Phys. 2018;5(1):22.
Spyridonidis T, Papathanasiou N, Spyridonidis J, et al. (90)Y-microsphere radioembolization: the method, clinical evidence and perspective. Hell J Nucl Med. 2020;23(3):330-338.
Kim SP, Cohalan C, Kopek N, Enger SA. A guide to (90)Y radioembolization and its dosimetry. Phys Med. 2019;68:132-145.
Haste P, Tann M, Persohn S, et al. Correlation of technetium-99m macroaggregated albumin and yttrium-90 glass microsphere biodistribution in hepatocellular carcinoma: a retrospective review of pretreatment single photon emission CT and posttreatment positron emission tomography/CT. J Vasc Interv Radiol. 2017;28(5):722-730. e721.
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. Medical Internal Radiation Dose Committee. J Nucl Med. 1999;40(1):11S-36S.
Fu J, Wang H. Precision diagnosis and treatment of liver cancer in China. Cancer Lett. 2018;412:283-288.
Kim AY, Frantz S, Brower J, Akhter N. Radioembolization with yttrium-90 microspheres for the treatment of liver metastases of pancreatic adenocarcinoma: a multicenter analysis. J Vasc Interv Radiol. 2019;30(3):298-304. e292.
Allimant C, Kafrouni M, Delicque J, et al. Tumor targeting and three-dimensional voxel-based dosimetry to predict tumor response, toxicity, and survival after yttrium-90 resin microsphere radioembolization in hepatocellular carcinoma. J Vasc Interv Radiol. 2018;29(12):1662-1670. e1664.
Gil-Alzugaray B, Chopitea A, Inarrairaegui M, et al. Prognostic factors and prevention of radioembolization-induced liver disease. Hepatology. 2013;57(3):1078-1087.
Moran V, Prieto E, Sancho L, et al. Impact of the dosimetry approach on the resulting (90)Y radioembolization planned absorbed doses based on (99m)Tc-MAA SPECT-CT: is there agreement between dosimetry methods?. EJNMMI Phys. 2020;7(1):72.
Richetta E, Pasquino M, Poli M, et al. PET-CT post therapy dosimetry in radioembolization with resin (90)Y microspheres: comparison with pre-treatment SPECT-CT (99m)Tc-MAA results. Phys Med. 2019;64:16-23.
Wondergem M, Smits ML, Elschot M, et al. 99mTc-macroaggregated albumin poorly predicts the intrahepatic distribution of 90Y resin microspheres in hepatic radioembolization. J Nucl Med. 2013;54(8):1294-1301.
Sim Y, Chung MJ, Kotter E, et al. Deep Convolutional neural network-based software improves radiologist detection of malignant lung nodules on chest radiographs. Radiology. 2020;294(1):199-209.
Arabi H, Zaidi H. Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy. Eur J Hybrid Imaging. 2020;4(1):17.
Seifert R, Weber M, Kocakavuk E, Rischpler C, Kersting D. Artificial intelligence and machine learning in nuclear medicine: future perspectives. Semin Nucl Med. 2021;51(2):170-177.
Gatos I, Tsantis S, Karamesini M, et al. Focal liver lesions segmentation and classification in nonenhanced T2-weighted MRI. Med Phys. 2017;44(7):3695-3705.
Gatos I, Tsantis S, Spiliopoulos S, et al. Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment. Med Phys. 2019;46(5):2298-2309.
Choi H. Deep learning in nuclear medicine and molecular imaging: current perspectives and future directions. Nucl Med Mol Imaging. 2018;52(2):109-118.
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.
Divgi C, Carrasquillo JA, Meredith R, et al. Overcoming barriers to radiopharmaceutical therapy (RPT): an overview from the NRG-NCI Working Group on dosimetry of radiopharmaceutical therapy. Int J Radiat Oncol Biol Phys. 2021;109(4):905-912.
Xiao Y, Roncali E, Hobbs R, et al. Toward individualized voxel-level dosimetry for radiopharmaceutical therapy. Int J Radiat Oncol Biol Phys. 2021;109(4):902-904.
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
Kearney V, Chan JW, Wang TQ, et al. DoseGAN: a generative adversarial network for synthetic dose prediction using attention-gated discrimination and generation. Sci Rep-Uk. 2020;10(1):11073.
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 https://doi.org/10.1038/s41598-019-46620-y
Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Paper presented at 27th International Conference on Neural Information Processing Systems 2014. p. 2672-80
Zhu J-Y, Park T, Isola P, Efros AA, Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv:170310593 [csCV]. 2020.
Isola P, Zhu J-Y, Zhou T, Efros AA, Image-to-image translation with conditional adversarial networks. arXiv:161107004v3 [csCV]. 2018.
Mejjati YA, Richardt C, Tompkin J, Cokser D, Kim KI, Unsupervised attention-guided Image to Image Translation. arXiv:180602311v3. 2018.
Kingma DP, Ba J, Adam: a method for stochastic optimization. arXiv:14126980v9. 2017.
Jaccard P. The distribution of the flora in the alpine zone. New Phytol. 1912;11(2):37-50.
Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015;15:29.
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 kernel. Cancer Biother Radiopharm. 2021.
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.
Papadimitroulas P. Dosimetry applications in GATE Monte Carlo toolkit. Phys Med. 2017;41:136-140.
Jan S, Benoit D, Becheva E, et al. GATE V6: a major enhancement of the GATE simulation platform enabling modelling of CT and radiotherapy. Phys Med Biol. 2011;56(4):881-901.
Tong AK, Kao YH, Too CW, Chin KF, Ng DC, Chow PK. Yttrium-90 hepatic radioembolization: clinical review and current techniques in interventional radiology and personalized dosimetry. Br J Radiol. 2016;89(1062):20150943.
LNHB. Y-90 tables. 2021. Available from: http://www.lnhb.fr/nuclides/Y-90_tables.pdf. (Accessed September 22, 2021).
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(8):5238-5247.
Flux G, Bardies M, Chiesa C, et al. Clinical radionuclide therapy dosimetry: the quest for the “Holy Gray”. Eur J Nucl Med Mol Imaging. 2007;34(10):1699-1700.
Kao YH, Tan EH, Ng CE, Goh SW. Clinical implications of the body surface area method versus partition model dosimetry for yttrium-90 radioembolization using resin microspheres: a technical review. Ann Nucl Med. 2011;25(7):455-461.
Sze DY, Lam MG. Reply to “The limitations of theoretical dose modeling for yttrium-90 radioembolization” . J Vasc Interv Radiol. 2014;25(7):1147-1148.
Lam MG, Louie JD, Abdelmaksoud MH, Fisher GA, Cho-Phan CD, Sze DY. Limitations of body surface area-based activity calculation for radioembolization of hepatic metastases in colorectal cancer. J Vasc Interv Radiol. 2014;25(7):1085-1093.
Chiesa C, Maccauro M. (166)Ho microsphere scout dose for more accurate radioembolization treatment planning. Eur J Nucl Med Mol Imaging. 2020;47(4):744-747.
Gnesin S, Canetti L, Adib S, et al. Partition model-based 99mTc-MAA SPECT/CT predictive dosimetry compared with 90Y TOF PET/CT posttreatment dosimetry in radioembolization of hepatocellular carcinoma: a quantitative agreement comparison. J Nucl Med. 2016;57(11):1672-1678.
Jadoul A, Bernard C, Lovinfosse P, et al. Comparative dosimetry between (99m)Tc-MAA SPECT/CT and (90)Y PET/CT in primary and metastatic liver tumors. Eur J Nucl Med Mol Imaging. 2020;47(4):828-837.
Chiesa C, Mira M, De Nile MC, Maccauro M, Spreafico C, Zanette C. Discrepancy between 99mTc-MAA SPECT and 90Y glass microspheres PET lung dosimetry in radioembolization of hepatocarcinoma. EANM 2016;16.
Jiang M, Fischman A, Nowakowski FS, et al. Segmental perfusion differences on paired Tc-99m macroaggregated albumin (MAA) hepatic perfusion imaging and yttrium-90 (Y-90) Bremsstrahlung imaging studies in sir-sphere radioembolization: associations with angiography. J Nucl Med Rad Ther. 2012;3:1.
Knesaurek K, Machac J, Muzinic M, DaCosta M, Zhang Z, Heiba S. Quantitative comparison of yttrium-90 (90Y)-microspheres and technetium-99m (99mTc)-macroaggregated albumin SPECT images for planning 90Y therapy of liver cancer. Technol Cancer Res Treat. 2010;9(3):253-262.
Papadimitroulas P, Loudos G, Le Maitre A, et al. Investigation of realistic PET simulations incorporating tumor patient's specificity using anthropomorphic models: creation of an oncology database. Med Phys. 2013;40(11):112506.
Ilhan H, Goritschan A, Paprottka P, et al. Systematic evaluation of tumoral 99mTc-MAA uptake using SPECT and SPECT/CT in 502 patients before 90Y radioembolization. J Nucl Med. 2015;56(3):333-338.
Gaba RC. Planning arteriography for yttrium-90 microsphere radioembolization. Semin Intervent Radiol. 2015;32(4):428-438.
Wang T, Lei Y, Fu Y, Curran WJ, Liu T, Yang X, Machine learning in quantitative PET imaging. arXiv:200106597v1 [eessIV]. 2020.
Otto K. Volumetric modulated arc therapy: iMRT in a single gantry arc. Med Phys. 2008;35(1):310-317.
Kearney V, Chan JW, Valdes G, Solberg TD, Yom SS. The application of artificial intelligence in the IMRT planning process for head and neck cancer. Oral Oncol. 2018;87:111-116.
Buatti JM, Pryma DA, Kiess AP, et al. A framework for patient-centered pathways of care for radiopharmaceutical therapy: an ASTRO consensus document. Int J Radiat Oncol Biol Phys. 2021;109(4):913-922.
St James S, Bednarz B, Benedict S, et al. Current status of radiopharmaceutical therapy. Int J Radiat Oncol Biol Phys. 2021;109(4):891-901.