Knowledge-based isocenter selection in radiosurgery planning.
Gamma Knife
deep learning
knowledge based planning
machine learning
radiosurgery
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:
27
01
2020
revised:
27
04
2020
accepted:
19
05
2020
pubmed:
31
5
2020
medline:
15
5
2021
entrez:
31
5
2020
Statut:
ppublish
Résumé
We present a new method for knowledge-based isocenter selection for treatment planning in radiosurgery. Our objective is to develop a prediction model that can learn from past manually designed treatment plans. We leverage recent advances in deep learning to predict isocenter locations in treatment plans in order to provide a decision support tool. The proposed method adapts a geometric approach using orthogonal moment expansions as a feature vector for describing the shape of the tumor. Our approach accounts primarily for tumor shape and OAR proximity, the two factors that are known to greatly affect the isocenter placement. We solve the prediction problem by training a residual neural network with skip connections on the formed shape descriptors. Our network was trained on 533 patient cases and was validated on a set of out-of-sample cases. Our method generates heatmap predictions for isocenter locations that are in most cases comparable to the experienced human planners, which shows that the method can be used in treatment planning to guide the users for determining the isocenters. Our numerical experiments indicate a positive predictive value on an independent validation set when compared against a test dataset that was not seen by the model during training.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3913-3927Informations de copyright
© 2020 American Association of Physicists in Medicine.
Références
CCSAC, Canadian Cancer Statistics 2017, 2017, http://www.cancer.ca/media/cancer.ca/CW/cancer /media/cancer.ca/CW/cancer [Accessed: July 31, 2017].
Stelzer KJ. Epidemiology and prognosis of brain metastases. Surg Neurol Int. 2013;4:S192.
Doudareva E, Ghobadi K, Aleman DM, Ruschin M, Jaffray DA. Skeletonization for isocentre selection in Gamma Knife\circledR PerfexionTM. TOP. 2015;23:369-385.
Ferris MC, Lim J, Shepard DM. An optimization approach for radiosurgery treatment planning. SIAM J Optim. 2002;13:921-937.
Flickinger JC, DadeLunsford L, Wu A, Maitz AH, Kalend AM. Treatment planning for gamma knife radiosurgery with multiple isocenters. Int J Radiat Oncol Biol Phys. 1990;18:1495-1501.
Ghobadi K. Optimization methods for patient positioning in Leksell Gamma Knife Perfexion, PhD thesis, 2014.
Wu QJ, Bourland JD. Morphology-guided radiosurgery treatment planning and optimization for multiple isocenters. Med Phys. 1999;26:2151-2160.
Zhang P, Wu J, Dean D, et al. Plug pattern optimization for gamma knife radiosurgerytreatment planning. Int J Radiat Oncol Biol Phys. 2003;55:420-427.
Ghaffari HR, Aleman DM, Jaffray DA, Ruschin M. Incorporation of delivery times in stereotactic radiosurgery treatmentoptimization. J Global Optim. 2017;69:103-115.
Ghobadi K, Ghaffari HR, Aleman DM, Jaffray DA, Ruschin M. Automated treatment planning for a dedicated multi-source intracranial radiosurgery treatment unit using projected gradient and grassfire algorithms. Med Phys. 2012;39:3134-3141.
Flickinger JC, Sneed PK, Larson DA. A multi-institutional experience with stereotactic radiosurgery for solitary brain metastasis. Int J Radiat Oncol Biol Phys. 1994;28:797-802.
Wang J. Packing of unequal spheres and automated radiosurgical treatment planning. J. Combinatorial Optim. 1999;3:453-463.
Luan S, Swanson N, Chen Z, Ma L. Dynamic gamma knife radiosurgery. Phys Med Biol. 2009;54:1579.
Blum H. A transformation for extracting descriptors of shape. 1967.
Wagner TH, Yi T, Meeks SL, et al. A geometrically based method for automated radiosurgery planning. Int J Radiat Oncol Biol Phys. 2000;48:1599-1611.
Cevik M, Aleman D, Lee Y. Simultaneous optimization of isocenter locations and sector duration in radiosurgery. Phys Med Biol. 2019;64:025010.
Flusser J, Suk T, Zitová B. 2D and 3D Image Analysis by Moments. Hoboken: John Wiley & Sons; 2016.
Hoffman K, Kunze R, Linear Algebra. 1990.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks, in European Conference on Computer Vision, Springer, 2016:630-645.
Li H, Xu Z, Taylor G. Studer C, Goldstein T. Visualizingthe loss landscape of neural nets, in Advances in Neural Information Processing Systems, 2018:6389-6399.
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167; 2015.
Ramachandran P, Zoph B, Le QV, Searching for activation functions, arXiv preprint arXiv:1710.05941: 2017.
Masters D, Luschi C. Revisiting Small Batch Training for Deep Neural Networks, arXiv preprint arXiv:1804.07612; 2018.
Bezanson J, Edelman A, Karpinski S, Shah VB. Julia: A fresh approach to numerical computing. SIAM review. 2017;59:65-98.
Innes M. Flux: Elegant machine learning with Julia. J Open Source Software. 2018;3:602.
Chanyavanich V, Das SK, Lee WR, Lo JY. Knowledge-based IMRT treatment planning for prostate cancer. Med Phys. 2011;38:2515-2522.
Kazhdan M, Simari P, McNutt T, et al. A shape relationship descriptor for radiation therapy planning, in International Conference on Medical Image Computingand Computer-Assisted Intervention, Springer, Berlin, Heidelberg, 2009:100-108.
Petit SF, Wu B, Kazhdan M, et al. Increased organ sparing usingshape-based treatment plan optimization for intensity modulated radiation therapy of pancreatic adenocarcinoma. Radiother Oncol. 2012;102:38-44.
Simari P, Wu B, Jacques R, et al A statistical approach for achievable dose querying in IMRT planning, in International Conference on Medical Image Computingand Computer-Assisted Intervention, Springer, Berlin, Heidelberg, 2010:521-528.
Wu B, Ricchetti F, Sanguineti G, et al. Data-driven approach to generating achievable dose-volume histogram objectives in intensity-modulated radiotherapy planning. Int J Radiat Oncol Biol Phys. 2011;79:1241-1247.
Wu B, Ricchetti F, Sanguineti G, et al. Patient geometry-driven information retrieval for IMRT treatment plan quality control. Med Phys. 2009;36:5497-5505.
Cover TM, Thomas JA. Elements of Information Theory. Hoboken:John Wiley & Sons; 2012.
Shiraishi S, Moore KL. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy. Med Phys. 2016;43:378-387.
Ge Y, Wu QJ. Knowledge-based planning for intensity-modulated radiation therapy: a review of data-driven approaches. Med Phys. 2019;46:2760-2775.
Merkow J, Marsden A, Kriegman D, Tu Z. Dense volume-to-volume vascular boundary detection, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2016:371-379.