Proton range uncertainty caused by synthetic computed tomography generated with deep learning from pelvic magnetic resonance imaging

References

• Boulanger M, Nunes J-C, Chourak H, et al. Deep learning methods to generate synthetic CT from MRI in radiotherapy: a literature review. Phys Med. 2021;89:265–281. doi: 10.1016/j.ejmp.2021.07.027.
   PubMed Web of Science ®Google Scholar
• Hoffmann A, Oborn B, Moteabbed M, et al. MR-guided proton therapy: a review and a preview. Radiat Oncol. 2020;15(1):129. doi: 10.1186/s13014-020-01571-x.
   PubMed Web of Science ®Google Scholar
• Tyagi N, Fontenla S, Zhang J, et al. Dosimetric and workflow evaluation of first commercial synthetic CT software for clinical use in pelvis. Phys Med Biol. 2017;62(8):2961–2975. doi: 10.1088/1361-6560/aa5452.
   PubMed Web of Science ®Google Scholar
• Liu L, Jolly S, Cao Y, et al. Female pelvic synthetic CT generation based on joint intensity and shape analysis. Phys Med Biol. 2017;62(8):2935–2949. doi: 10.1088/1361-6560/62/8/2935.
   PubMed Web of Science ®Google Scholar
• Largent A, Barateau A, Nunes J-C, et al. Pseudo-CT generation for MRI-only radiation therapy treatment planning: comparison among patch-based, atlAS-BASED, and bulk density methods. Int J Radiat Oncol Biol Phys. 2019;103(2):479–490. doi: 10.1016/j.ijrobp.2018.10.002.
   PubMed Web of Science ®Google Scholar
• Dowling JA, Sun J, Pichler P, et al. Automatic substitute computed tomography generation and contouring for magnetic resonance imaging (MRI)-alone external beam radiation therapy from standard MRI sequences. Int J Radiat Oncol Biol Phys. 2015;93(5):1144–1153. doi: 10.1016/j.ijrobp.2015.08.045.
   PubMed Web of Science ®Google Scholar
• Cusumano D, Placidi L, Teodoli S, et al. On the accuracy of bulk synthetic CT for MR-guided online adaptive radiotherapy. Radiol Med. 2020;125(2):157–164. doi: 10.1007/s11547-019-01090-0.
   PubMed Web of Science ®Google Scholar
• Choi JH, Lee D, O'Connor L, et al. Bulk anatomical density based dose calculation for patient-specific quality assurance of MRI-Only prostate radiotherapy. Front Oncol. 2019;9:997. doi: 10.3389/fonc.2019.00997.
   PubMed Web of Science ®Google Scholar
• Kemppainen R, Suilamo S, Ranta I, et al. Assessment of dosimetric and positioning accuracy of a magnetic resonance imaging-only solution for external beam radiotherapy of pelvic anatomy. Phys Imaging Radiat Oncol. 2019;11:1–8. doi: 10.1016/j.phro.2019.06.001.
   PubMedGoogle Scholar
• Arabi H, Koutsouvelis N, Rouzaud M, et al. Atlas-guided generation of pseudo-CT images for MRI-only and hybrid PET–MRI-guided radiotherapy treatment planning. Phys Med Biol. 2016;61(17):6531–6552. doi: 10.1088/0031-9155/61/17/6531.
   PubMed Web of Science ®Google Scholar
• Guerreiro F, Burgos N, Dunlop A, et al. Evaluation of a multi-atlas CT synthesis approach for MRI-only radiotherapy treatment planning. Phys Med. 2017;35:7–17. doi: 10.1016/j.ejmp.2017.02.017.
   PubMed Web of Science ®Google Scholar
• Persson E, Gustafsson C, Nordström F, et al. MR-OPERA: a multicenter/multivendor validation of magnetic resonance imaging–only prostate treatment planning using synthetic computed tomography images. Int J Radiat Oncol Biol Phys. 2017;99(3):692–700. doi: 10.1016/j.ijrobp.2017.06.006.
   PubMed Web of Science ®Google Scholar
• Chen S, Quan H, Qin A, et al. MR image-based synthetic CT for IMRT prostate treatment planning and CBCT image-guided localization. J Appl Clin Med Phys. 2016;17(3):236–245. doi: 10.1120/jacmp.v17i3.6065.
   PubMed Web of Science ®Google Scholar
• Huynh T, Gao Y, Kang J, et al. Estimating CT image from MRI data using structured random forest and auto-context model. IEEE Trans Med Imaging. 2016;35(1):174–183. doi: 10.1109/TMI.2015.2461533.
   PubMed Web of Science ®Google Scholar
• Spadea MF, Pileggi G, Zaffino P, et al. Deep convolution neural network (DCNN) multiplane approach to synthetic CT generation from MR images—application in brain proton therapy. Int J Radiat Oncol Biol Phys. 2019;105(3):495–503. doi: 10.1016/j.ijrobp.2019.06.2535.
   PubMed Web of Science ®Google Scholar
• Neppl S, Landry G, Kurz C, et al. Evaluation of proton and photon dose distributions recalculated on 2D and 3D unet-generated pseudoCTs from T1-weighted MR head scans. Acta Oncol. 2019;58(10):1429–1434. doi: 10.1080/0284186X.2019.1630754.
   PubMed Web of Science ®Google Scholar
• Kazemifar S, Barragán Montero AM, Souris K, et al. Dosimetric evaluation of synthetic CT generated with GANs for MRI‐only proton therapy treatment planning of brain tumors. J Appl Clin Med Phys. 2020;21(5):76–86. doi: 10.1002/acm2.12856.
   PubMed Web of Science ®Google Scholar
• Thummerer A, De Jong BA, Zaffino P, et al. Comparison of the suitability of CBCT- and MR-based synthetic CTs for daily adaptive proton therapy in head and neck patients. Phys Med Biol. 2020;65(23):235036. doi: 10.1088/1361-6560/abb1d6.
   PubMed Web of Science ®Google Scholar
• Florkow MC, Guerreiro F, Zijlstra F, et al. Deep learning-enabled MRI-only photon and proton therapy treatment planning for paediatric abdominal tumours. Radiother Oncol. 2020;153:220–227. doi: 10.1016/j.radonc.2020.09.056.
   PubMed Web of Science ®Google Scholar
• Liu Y, Lei Y, Wang Y, et al. Evaluation of a deep learning-based pelvic synthetic CT generation technique for MRI-based prostate proton treatment planning. Phys Med Biol. 2019;64(20):205022. doi: 10.1088/1361-6560/ab41af.
   PubMed Web of Science ®Google Scholar
• Maspero M, Bentvelzen LG, Savenije MHF, et al. Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy. Radiother Oncol. 2020;153:197–204. doi: 10.1016/j.radonc.2020.09.029.
   PubMed Web of Science ®Google Scholar
• Liu Y, Lei Y, Wang Y, et al. MRI-based treatment planning for proton radiotherapy: dosimetric validation of a deep learning-based liver synthetic CT generation method. Phys Med Biol. 2019;64(14):145015. doi: 10.1088/1361-6560/ab25bc.
   PubMed Web of Science ®Google Scholar
• Shafai-Erfani G, Lei Y, Liu Y, et al. MRI-based proton treatment planning for base of skull tumors. Int J Part Ther. 2019;6(2):12–25. doi: 10.14338/IJPT-19-00062.1.
   PubMedGoogle Scholar
• Paganetti H. Relative biological effectiveness (RBE) values for proton beam therapy. Variations as a function of biological endpoint, dose, and linear energy transfer. Phys Med Biol. 2014;59(22):R419–R472. doi: 10.1088/0031-9155/59/22/R419.
   PubMed Web of Science ®Google Scholar
• Fetty L, Löfstedt T, Heilemann G, et al. Investigating conditional GAN performance with different generator architectures, an ensemble model, and different MR scanners for MR-sCT conversion. Phys Med Biol. 2020;65(10):105004. doi: 10.1088/1361-6560/ab857b.
   PubMed Web of Science ®Google Scholar
• Cusumano D, Lenkowicz J, Votta C, et al. A deep learning approach to generate synthetic CT in low field MR-guided adaptive radiotherapy for abdominal and pelvic cases. Radiother Oncol. 2020;153:205–212. doi: 10.1016/j.radonc.2020.10.018.
   PubMed Web of Science ®Google Scholar
• Qi M, Li Y, Wu A, et al. Multi‐sequence MR image‐based synthetic CT generation using a generative adversarial network for head and neck MRI‐only radiotherapy. Med Phys. 2020;47(4):1880–1894. doi: 10.1002/mp.14075.
   PubMed Web of Science ®Google Scholar
• Olberg S, Zhang H, Kennedy WR, et al. Synthetic CT reconstruction using a deep spatial pyramid convolutional framework for MR‐only breast radiotherapy. Med Phys. 2019;46(9):4135–4147. doi: 10.1002/mp.13716.
   PubMed Web of Science ®Google Scholar
• Brou Boni KND, Klein J, Vanquin L, et al. MR to CT synthesis with multicenter data in the pelvic area using a conditional generative adversarial network. Phys Med Biol. 2020;65(7):075002. doi: 10.1088/1361-6560/ab7633.
   PubMed Web of Science ®Google Scholar
• Koike Y, Akino Y, Sumida I, et al. Feasibility of synthetic computed tomography generated with an adversarial network for multi-sequence magnetic resonance-based brain radiotherapy. J Radiat Res. 2020;61(1):92–103. doi: 10.1093/jrr/rrz063.
   PubMed Web of Science ®Google Scholar
• Maspero M, Savenije MHF, Dinkla AM, et al. Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy. Phys Med Biol. 2018;63(18):185001. doi: 10.1088/1361-6560/aada6d.
   PubMed Web of Science ®Google Scholar
• Tie X, Lam S, Zhang Y, et al. Pseudo‐CT generation from multi‐parametric MRI using a novel multi‐channel multi‐path conditional generative adversarial network for nasopharyngeal carcinoma patients. Med Phys. 2020;47(4):1750–1762. doi: 10.1002/mp.14062.
   PubMed Web of Science ®Google Scholar
• Tang B, Wu F, Fu Y, et al. Dosimetric evaluation of synthetic CT image generated using a neural network for MR‐only brain radiotherapy. J Appl Clin Med Phys. 2021;22(3):55–62. doi: 10.1002/acm2.13176.
   PubMed Web of Science ®Google Scholar
• Bourbonne V, Jaouen V, Hognon C, et al. Dosimetric validation of a GAN-based pseudo-CT generation for MRI-only stereotactic brain radiotherapy. Cancers. 2021;13(5):1082. doi: 10.3390/cancers13051082.
   PubMed Web of Science ®Google Scholar
• Sharma A, Hamarneh G. Missing MRI pulse sequence synthesis using multi-modal generative adversarial network. IEEE Trans Med Imaging. 2020;39(4):1170–1183. doi: 10.1109/TMI.2019.2945521.
   PubMed Web of Science ®Google Scholar
• Matt. H, Brige C, Mark, R, et al. Deep generative model for Synthetic-CT generation with uncertainty predictions. In: Martel AL, Abolmaesumi P, Stoyanov D, et al. editors. Med image comput comput assist interv – MICCAI 2020 [internet]. Cham: springer International Publishing; 2020 [cited 2023 May 11]. p. 834–844. Available from: 10.1007/978-3-030-59710-8_81.
   Google Scholar
• Isola P, Zhu J-Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks. 2017 IEEE Conf Comput Vis Pattern Recognit CVPR [Internet]. Honolulu, HI: IEEE; 2017 [cited 2023 May 9]. p. 5967–5976. Available from: http://ieeexplore.ieee.org/document/8100115/.
   Google Scholar
• Nyholm T, Svensson S, Andersson S, et al. MR and CT data with multiobserver delineations of organs in the pelvic area-part of the gold atlas project. Med Phys. 2018;45(3):1295–1300. doi: 10.1002/mp.12748.
   PubMed Web of Science ®Google Scholar
• Juntu J, Sijbers J, Dyck D, et al. Bias field correction for MRI images. In: kurzyński M, Puchała E, Woźniak M editors. Comput recognit syst [internet]. Berlin, Heidelberg: Springer Berlin Heidelberg; 2005 [cited 2023 Jul 18]. p. 543–551. Available from: 10.1007/3-540-32390-2_64.
   Google Scholar
• Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15:1929–1958.
   Web of Science ®Google Scholar
• Perl J, Shin J, Schümann J, et al. TOPAS: an innovative proton monte carlo platform for research and clinical applications: TOPAS: an innovative proton monte carlo platform. Med Phys. 2012;39(11):6818–6837. doi: 10.1118/1.4758060.
   PubMed Web of Science ®Google Scholar
• Hu S, Pezzotti N, Welling M, et al. Learning to predict error for MRI reconstruction. In: de Bruijne M, Cattin PC, Cotin S editors. Med image comput comput assist interv – MICCAI 2021 [internet]. Cham: springer International Publishing; 2021 [cited 2023 Jul 10]. p. 604–613. Available from: 10.1007/978-3-030-87199-4_57.
   Google Scholar
• Kendall A, Gal Y. What uncertainties do we need in bayesian deep learning for computer vision? 2017 [cited 2023 Jul 14]; Available from: https://arxiv.org/abs/1703.04977.
   Google Scholar
• Bragman FJS, Tanno R, Eaton-Rosen Z, et al. Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning. In: Frangi AF, Schnabel JA, Davatzikos C, editors. Med image comput comput assist interv – MICCAI 2018 [internet]. Cham: springer International Publishing; 2018 [cited 2023 Jul 14]. p. 3–11. Available from: 10.1007/978-3-030-00937-3_1.
   Google Scholar
• Hüllermeier E, Waegeman W. Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach Learn. 2021;110(3):457–506. doi: 10.1007/s10994-021-05946-3.
   Web of Science ®Google Scholar
• Sedlmeier A, Gabor T, Phan T, et al. Uncertainty-based out-of-distribution classification in deep reinforcement learning. Proc 12th Int Conf Agents Artif Intell [Internet]. Valletta, Malta: SCITEPRESS - Science and Technology Publications; 2020 [cited 2023 Jul 5]. p. 522–529. Available from: doi: 10.5220/0008949905220529.
   Google Scholar
• Gal Y, Ghahramani Z. Dropout as a Bayesian approximation: representing model uncertainty in deep learning [Internet]. arXiv; 2016 [cited 2023 May 11]. Available from: http://arxiv.org/abs/1506.02142.
   Google Scholar
• Pileggi G, Speier C, Sharp GC, et al. Proton range shift analysis on brain pseudo-CT generated from T1 and T2 MR. Acta Oncol. 2018;57(11):1521–1531. doi: 10.1080/0284186X.2018.1477257.
   PubMed Web of Science ®Google Scholar
• Florkow MC, Zijlstra F, Kerkmeijer LGW, et al. The impact of MRI-CT registration errors on deep learning-based synthetic CT generation. In: Angelini ED, Landman BA, editors. Med imaging 2019 image process [Internet]. San Diego, United States: SPIE; 2019 [cited 2023 Jul 12]. p. 116. Available from: doi: 10.1117/12.2512747.
   Google Scholar
• Wyatt JJ, Kaushik S, Cozzini C, et al. Comprehensive dose evaluation of a deep learning based synthetic computed tomography algorithm for pelvic magnetic resonance-only radiotherapy. Radiother Oncol. 2023;184:109692. doi: 10.1016/j.radonc.2023.109692.
   PubMed Web of Science ®Google Scholar
• Näsmark T, Andersson J. Proton stopping power prediction based on dual‐energy CT‐generated virtual monoenergetic images. Med Phys. 2021;48(9):5232–5243. doi: 10.1002/mp.15066.
   PubMed Web of Science ®Google Scholar
• Permatasari FF, Eulitz J, Richter C, et al. Material assignment for proton range prediction in monte carlo patient simulations using stopping-power datasets. Phys Med Biol. 2020;65(18):185004. doi: 10.1088/1361-6560/ab9702.
   PubMed Web of Science ®Google Scholar