Fast geometric distortion correction using a deep neural network: Implementation for the 1 Tesla MRI-Linac system.
MRI-Linac
geometric distortion correction
gradient nonlinearity
neural network
phantom
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Sep 2020
Sep 2020
Historique:
received:
17
04
2020
revised:
18
06
2020
accepted:
04
07
2020
pubmed:
11
7
2020
medline:
15
5
2021
entrez:
11
7
2020
Statut:
ppublish
Résumé
Combining high-resolution magnetic resonance imaging (MRI) with a linear accelerator (Linac) as a single MRI-Linac system provides the capability to monitor intra-fractional motion and anatomical changes during radiotherapy, which facilitates more accurate delivery of radiation dose to the tumor and less exposure to healthy tissue. The gradient nonlinearity (GNL)-induced distortions in MRI, however, hinder the implementation of MRI-Linac system in image-guided radiotherapy where highly accurate geometry and anatomy of the target tumor is indispensable. To correct the geometric distortions in MR images, in particular, for the 1 Tesla (T) MRI-Linac system, a deep fully connected neural network was proposed to automatically learn the intricate relationship between the undistorted (theoretical) and distorted (real) space. A dataset, consisting of spatial samples acquired by phantom measurement that covers both inside and outside the working diameter of spherical volume (DSV), was utilized for training the neural network, which offers the ability to describe subtle deviations of the GNL field within the entire region of interest (ROI). The performance of the proposed method was evaluated on MR images of a three-dimensional (3D) phantom and the pelvic region of an adult volunteer scanned in the 1T MRI-Linac system. The experimental results showed that the severe geometric distortions within the entire ROI had been successfully corrected with an error less than the pixel size. Also, the presented network is highly efficient, which achieved significant improvement in terms of computational efficiency compared to existing methods. The feasibility of the presented deep neural network for characterizing the GNL field deviations in the 1T MRI-Linac system was demonstrated in this study, which shows promise in facilitating the MRI-Linac system to be routinely implemented in real-time MRI-guided radiotherapy.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4303-4315Informations de copyright
© 2020 American Association of Physicists in Medicine.
Références
Dinauer PA, Brixey CJ, Moncur JT, Fanburg-Smith JC, Murphey MD. Pathologic and MR imaging features of benign fibrous soft-tissue tumors in adults. Radiographics. 2007;27:173-115.
Wu JS, Hochman MG. Soft-tissue tumors and tumorlike lesions: a systematic imaging approach. Radiology. 2009;253:297-316.
Pollard JM, Wen ZF, Sadagopan R, Wang JH, Ibbott GS. The future of image-guided radiotherapy will be MR guided. Br J Radiol. 2017;90.
Bitar R, Leung G, Perng R, et al. MR pulse sequences: what every radiologist wants to know but is afraid to ask. Radiographics. 2006;26:513-515.
Ladd ME, Bachert P, Meyerspeer M, et al. Pros and cons of ultra-high-field MRI/MRS for human application. Prog Nucl Mag Res Sp. 2018;109:1-50.
Weinberger O, Winter L, Dieringer MA, et al. Local multi-channel RF surface coil versus body RF coil transmission for cardiac magnetic resonance at 3 tesla: which configuration is winning the game? PloS one. 2016;11:e0161863.
Dawson LA, Jaffray DA. Advances in image-guided radiation therapy. J Clin Oncol. 2007;25:938-946.
Fischer-Valuck BW, Henke L, Green O, et al. Two-and-a-half-year clinical experience with the world's first magnetic resonance image guided radiation therapy system. Adv Radiat Oncol. 2017;2:485-493.
Fast M, van de Schoot A, van de Lindt T, Carbaat C, van der Heide U, Sonke JJ. Tumor trailing for liver SBRT on the MR-linac. Int J Radiat Oncol. 2019;103:468-478.
Bainbridge HE, Menten MJ, Fast MF, Nill S, Oelfke U, McDonald F. Treating locally advanced lung cancer with a 1.5 T MR-Linac-effects of the magnetic field and irradiation geometry on conventionally fractionated and isotoxic dose-escalated radiotherapy. Radiother Oncol. 2017;125:280-285.
Corradini S, Alongi F, Andratschke N, et al. MR-guidance in clinical reality: current treatment challenges and future perspectives. Radiat Oncol. 2019;14.
Tijssen RHN, Philippens MEP, Paulson ES, et al. MRI commissioning of 1.5T MR-linac systems - a multi-institutional study. Radiother Oncol. 2019;132:114-120.
Janke A, Zhao HW, Cowin GJ, Galloway GJ, Doddrell DM. Use of spherical harmonic deconvolution methods to compensate for nonlinear gradient effects on MRI images. Magnet Reson Med. 2004;52:115-122.
Keall PJ, Barton M, Crozier S. Program AM-L the Australian magnetic resonance imaging-linac program. Semin Radiat Oncol. 2014;24:203-206.
Liu LM, Sanchez-Lopez H, Liu F, Crozier S. Flanged-edge transverse gradient coil design for a hybrid LINAC-MRI system. J Magn Reson. 2013;226:70-78.
Tang F, Freschi F, Lopez HS, Repetto M, Liu F, Crozier S. Intra-coil interactions in split gradient coils in a hybrid MRI-LINAC system. J Magn Reson. 2016;265:52-58.
Doran SJ, Charles-Edwards L, Reinsberg SA, Leach MO. A complete distortion correction for MR images: I. Gradient warp correction. Phys Med Biol. 2005;50:1343-1361.
Glide-Hurst CK, Wen N, Hearshen D, et al. Initial clinical experience with a radiation oncology dedicated open 1.0T MR-simulation. J Appl Clin Med Phys. 2015;16:218-240.
Tao S, Trzasko JD, Gunter JL, et al. Gradient nonlinearity calibration and correction for a compact, asymmetric magnetic resonance imaging gradient system. Phys Med Biol. 2017;62:N18-N31.
Shan SS, Liney GP, Tang FF, et al. Geometric distortion characterization and correction for the 1.0 T Australian MRI-linac system using an inverse electromagnetic method. Med Phys. 2020;47:1126-1138.
Weavers PT, Tao SZ, Trzasko JD, et al Image-based gradient non-linearity characterization to determine higher-order spherical harmonic coefficients for improved spatial position accuracy in magnetic resonance imaging. Magn Reson Imaging. 2017;38:54-62.
Poole M, Bowtell R. Novel gradient coils designed using a boundary element method. Concept Magn Reson B. 2007;31B:162-175.
Cobos SC. Forward and inverse analysis of electromagnetic fields for MRI using computational techniques. University of Nottingham; 2008.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436-444.
Schmidhuber J. Deep learning in neural networks: an overview. Neural Networks. 2015;61:85-117.
He KM, Zhang XY, Ren SQ, Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. 2015 IEEE International Conference on Computer Vision (Iccv). 2015;123:1026-1034. https://doi.org/10.1109/Iccv.2015
Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2:230-243.
Wang DM, Doddrell DM, Cowin G. A novel phantom and method for comprehensive 3-dimensional measurement and correction of geometric distortion in magnetic resonance imaging. Magn Reson Imaging. 2004;22:529-542.
Shan SS, Li MY, Tang FF, Ma H, Liu F, Crozier S. Gradient field deviation (GFD) correction using a hybrid-norm approach with wavelet sub-band dependent regularization: implementation for radial MRI at 9.4 T. IEEE Trans Bio-Med Eng. 2019;66:2693-2701.
Price RR, Axel L, Morgan T, et al. Quality assurance methods and phantoms for magnetic-resonance-imaging - report of AAPM nuclear-magnetic-resonance task group no-1. Med Phys. 1990;17:287-295.
Pallotta S, Marrazzo L, Bucciolini M. Design and implementation of a water phantom for IMRT, arc therapy, and tomotherapy dose distribution measurements. Med Phys. 2007;34:3724-3731.
Seuntjens J, Olivares M, Evans M, Podgorsak E. Absorbed dose to water reference dosimetry using solid phantoms in the context of absorbed-dose protocols. Med Phys. 2005;32:2945-2953.
William Penny KF, Ashburner J, Kiebel S, Nichols T. Statistical Parametric Mapping: The Analysis of Functional Brain Images; 2007.
Walker A. Physics of MR image distortion: Impact on breast cancer. radiotherapy; 2015.
Walker A, Liney G, Metcalfe P, Holloway L. MRI distortion: considerations for MRI based radiotherapy treatment planning. Australas Phys Eng Sci Med. 2014;37:103-113.
Liney GP, Dong B, Weber E, et al. Imaging performance of a dedicated radiation transparent RF coil on a 1.0 Tesla inline MRI-linac. Phys Med Biol. 2018;63:135005.
Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. International Conference on International Conference on Machine Learning; February 01, 2015; 2015.
Kingma DP, Adam Ba J. A Method for Stochastic Optimization. ICLR; December 01, 2014, 2015.
Klambauer G, Unterthiner T, Mayr A, Hochreiter S. Self-normalizing neural networks. Adv Neur In. 2017;30.
Hoffer E, Hubara I, Soudry D. Train longer, generalize better: closing the generalization gap in large batch training of neural networks. Adv Neur In. 2017;30.
Glorot X, Bordes A, Bengio Y.Deep sparse rectifier neural networks. In Proc. 14th International Conference on Artificial Intelligence and Statistics 2011:315-323.
Zhang H, Weng TW, Chen PY, Hsieh CJ, Daniel L. Efficient Neural Network Robustness Certification with General Activation Functions. Advances in Neural Information Processing Systems 31. 2018;31.
Imani E, White M. Improving Regression Performance with Distributional Losses. Proceedings of the International Conference on Machine Learning; June 01, 2018, 2018.
Rodriguez JD, Perez A, Lozano JA. Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal. 2010;32:569-575.
Tao SZ, Trzasko JD, Shu YH, Huston J, Bernstein MA. Integrated image reconstruction and gradient nonlinearity correction. Magnet Reson Med. 2015;74:1019-1031.
Borman PTS, Tijssen RHN, Bos C, Moonen CTW, Raaymakers BW, Glitzner M. Characterization of imaging latency for real-time MRI-guided radiotherapy. Phys Med Biol. 2018;63:155023.
Ginn JS, Agazaryan N, Cao MS, et al. Characterization of spatial distortion in a 0.35 T MRI-guided radiotherapy system. Phys Med Biol. 2017;62:4525-4540.
Nejad-Davarani SP, Kim JP, Du DS, Glide-Hurst C. Large field of view distortion assessment in a low-field MR-linac. Med Phys. 2019;46:2347-2355.
Stanescu T, Jans HS, Wachowicz K, Fallone BG. Investigation of a 3D system distortion correction method for MR images. J Appl Clin Med Phys. 2010;11:200-216.
Dorsch S, Mann P, Elter A, et al. Measurement of isocenter alignment accuracy and image distortion of an 0.35 T MR-Linac system. Phys Med Biol. 2019;64:205011.
Keesman R, van de Lindt TN, Juan-Cruz C, et al. Correcting geometric image distortions in slice-based 4D-MRI on the MR-linac. Med Phys. 2019;46:3044-3054.
Du J, Ma GL, Li SH, et al. Ultrashort echo time (UTE) magnetic resonance imaging of the short T2 components in white matter of the brain using a clinical 3T scanner. NeuroImage. 2014;87:32-41.
Tao SZ, Trzasko JD, Shu YH, et al. NonCartesian MR image reconstruction with integrated gradient nonlinearity correction. Med Phys. 2015;42:7190-7201.