A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

Abstract

With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient’s PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 55

1. 1.

   Brahme A. Optimization of stationary and moving beam radiation therapy techniques. Radiotherapy and Oncology. 1988;12:129-140.

   Not in our library10.1016/0167-8140(88)90167-3

2. 2.

   Bortfeld T, Bürkelbach J, Boesecke R, Schlegel W. Methods of image reconstruction from projections applied to conformation radiotherapy. Physics in Medicine and Biology. 1990;35:1423.

   Not in our library10.1088/0031-9155/35/10/007

3. 3.

   Bortfeld TR, Kahler DL, Waldron TJ, Boyer AL. X-ray field compensation with multileaf collimators. International Journal of Radiation Oncology* Biology* Physics. 1994;28:723-730.

   Not in our library10.1016/0360-3016(94)90200-3

4. 4.

   Webb S. Optimisation of conformal radiotherapy dose distribution by simulated annealing. Physics in Medicine and Biology. 1989;34:1349.

   Not in our library10.1088/0031-9155/34/10/002

5. 5.

   Convery D, Rosenbloom M. The generation of intensity-modulated fields for conformal radiotherapy by dynamic collimation. Physics in Medicine and Biology. 1992;37:1359.

   Not in our library10.1088/0031-9155/37/6/012

6. 6.

   Xia P, Verhey LJ. Multileaf collimator leaf sequencing algorithm for intensity modulated beams with multiple static segments. Medical Physics. 1998;25:1424-1434.

   Not in our library10.1118/1.598315

7. 7.

   Keller-Reichenbecher M-A, et al. Intensity modulation with the “step and shoot” technique using a commercial MLC: A planning study. International Journal of Radiation Oncology* Biology* Physics. 1999;45:1315-1324.

   Not in our library10.1016/s0360-3016(99)00324-7

8. 8.

   Yu CX. Intensity-modulated arc therapy with dynamic multileaf collimation: an alternative to tomotherapy. Physics in Medicine and Biology. 1995;40:1435.

   Not in our library10.1088/0031-9155/40/9/004

9. 9.

   Otto K. Volumetric modulated arc therapy: IMRT in a single gantry arc. Medical physics. 2008;35:310-317.

   Not in our library10.1118/1.2818738

10. 10.

    Xing SMCaXWaCTaMWaL. Aperture modulated arc therapy. Physics in Medicine & Biology. 2003;48:1333.

    Not in our library10.1088/0031-9155/48/22/009

11. 11.

    Earl M, Shepard D, Naqvi S, Li X, Yu C. Inverse planning for intensity-modulated arc therapy using direct aperture optimization. Physics in medicine and biology. 2003;48:1075.

    Not in our library10.1088/0031-9155/48/8/309

12. 12.

    Cao, D., Afghan, M. K., Ye, J., Chen, F. & Shepard, D. M. A generalized inverse planning tool for volumetric-modulated arc therapy. Physics in Medicine & Biology54, 6725 (2009).

    Not in our library10.1088/0031-9155/54/21/018

13. 13.

    Shaffer R, et al. Volumetric Modulated Arc Therapy and Conventional Intensity-modulated Radiotherapy for Simultaneous Maximal Intraprostatic Boost: a Planning Comparison Study. Clinical Oncology. 2009;21:401-407.

    Not in our library10.1016/j.clon.2009.01.014

14. 14.

    Palma D, et al. Volumetric Modulated Arc Therapy for Delivery of Prostate Radiotherapy: Comparison With Intensity-Modulated Radiotherapy and Three-Dimensional Conformal Radiotherapy. International Journal of Radiation Oncology*Biology*Physics. 2008;72:996-1001.

    Not in our library10.1016/j.ijrobp.2008.02.047

15. 15.

    Penfold S, et al. Sparsity constrained split feasibility for dose-volume constraints in inverse planning of intensity-modulated photon or proton therapy. Physics in Medicine & Biology. 2017;62:3599.

    Not in our library10.1088/1361-6560/aa602b

16. 16.

    Craft DL, Halabi TF, Shih HA, Bortfeld TR. Approximating convex Pareto surfaces in multiobjective radiotherapy planning. Medical physics. 2006;33:3399-3407.

    Not in our library10.1118/1.2335486

17. 17.

    Craft DL, Hong TS, Shih HA, Bortfeld TR. Improved planning time and plan quality through multicriteria optimization for intensity-modulated radiotherapy. International Journal of Radiation Oncology* Biology* Physics. 2012;82:e83-e90.

    Not in our library10.1016/j.ijrobp.2010.12.007

18. 18.

    Monz M, Küfer K, Bortfeld T, Thieke C. Pareto navigation—algorithmic foundation of interactive multi-criteria IMRT planning. Physics in Medicine & Biology. 2008;53:985.

    Not in our library10.1088/0031-9155/53/4/011

19. 19.

    Nguyen D, et al. Dose domain regularization of MLC leaf patterns for highly complex IMRT plans. Medical Physics. 2015;42:1858-1870.

    Not in our library10.1118/1.4915286

20. 20.

    Nguyen D, et al. Computerized triplet beam orientation optimization for MRI-guided Co-60 radiotherapy. Medical Physics. 2016;43:5667-5675.

    Not in our library10.1118/1.4963212

21. 21.

    Nguyen D, et al. A comprehensive formulation for volumetric modulated arc therapy planning. Medical Physics. 2016;43:4263-4272.

    Not in our library10.1118/1.4953832

22. 22.

    Nguyen D, O’Connor D, Ruan D, Sheng K. Deterministic direct aperture optimization using multiphase piecewise constant segmentation. Medical Physics. 2017;44:5596-5609.

    Not in our library10.1002/mp.12529

23. 23.

    O’Connor D, Yu V, Nguyen D, Ruan D, Sheng K. Fraction-variant beam orientation optimization for non-coplanar IMRT. Physics in Medicine & Biology. 2018;63:045015.

    Not in our library10.1088/1361-6560/aaa94f

24. 24.

    Long, T., Chen, M., Jiang, S. B. & Lu, W. Threshold-driven optimization for reference-based auto-planning. Physics in medicine and biology (2018).

    Not in our library10.1088/1361-6560/aaa731

25. 25.

    Zarepisheh, M. et al. A DVH-guided IMRT optimization algorithm for automatic treatment planning and adaptive radiotherapy replanning. Medical Physics41, 061711-n/a, 10.1118/1.4875700 (2014).

    Not in our library10.1118/1.4875700

26. 26.

    Zhu X, et al. A planning quality evaluation tool for prostate adaptive IMRT based on machine learning. Medical physics. 2011;38:719-726.

    Not in our library10.1118/1.3539749

27. 27.

    Appenzoller LM, Michalski JM, Thorstad WL, Mutic S, Moore KL. Predicting dose-volume histograms for organs-at-risk in IMRT planning. Medical physics. 2012;39:7446-7461.

    Not in our library10.1118/1.4761864

28. 28.

    Wu B, et al. Improved robotic stereotactic body radiation therapy plan quality and planning efficacy for organ-confined prostate cancer utilizing overlap-volume histogram-driven planning methodology. Radiotherapy and Oncology. 2014;112:221-226.

    Not in our library10.1016/j.radonc.2014.07.009

29. 29.

    Shiraishi S, Tan J, Olsen LA, Moore KL. Knowledge-based prediction of plan quality metrics in intracranial stereotactic radiosurgery. Medical physics. 2015;42:908-917.

    Not in our library10.1118/1.4906183

30. 30.

    Moore KL, Brame RS, Low DA, Mutic S. Experience-Based Quality Control of Clinical Intensity-Modulated Radiotherapy Planning. International Journal of Radiation Oncology*Biology*Physics. 2011;81:545-551.

    Not in our library10.1016/j.ijrobp.2010.11.030

31. 31.

    Shiraishi S, Moore KL. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy. Medical physics. 2016;43:378-387.

    Not in our library10.1118/1.4938583

32. 32.

    Wu B, et al. Patient geometry-driven information retrieval for IMRT treatment plan quality control. Medical Physics. 2009;36:5497-5505.

    Not in our library10.1118/1.3253464

33. 33.

    Wu B, et al. Data-Driven Approach to Generating Achievable Dose–Volume Histogram Objectives in Intensity-Modulated Radiotherapy Planning. International Journal of Radiation Oncology*Biology*Physics. 2011;79:1241-1247.

    Not in our library10.1016/j.ijrobp.2010.05.026

34. 34.

    Wu, B. et al. Using overlap volume histogram and IMRT plan data to guide and automate VMAT planning: A head-and-neck case study. Medical Physics40, 021714-n/a, 10.1118/1.4788671 (2013).

    Not in our library10.1118/1.4788671

35. 35.

    Tran A, et al. Predicting liver SBRT eligibility and plan quality for VMAT and 4π plans. Radiation Oncology. 2017;12:70.

    Not in our library10.1186/s13014-017-0806-z

36. 36.

    Yuan L, et al. Quantitative analysis of the factors which affect the interpatient organ-at-risk dose sparing variation in IMRT plans. Medical Physics. 2012;39:6868-6878.

    Not in our library10.1118/1.4757927

37. 37.

    Lian, J. et al. Modeling the dosimetry of organ-at-risk in head and neck IMRT planning: An intertechnique and interinstitutional study. Medical Physics40, 121704-n/a, 10.1118/1.4828788 (2013).

    Not in our library10.1118/1.4828788

38. 38.

    Folkerts MM, Gu X, Lu W, Radke RJ, Jiang SB. SU-G-TeP1-09: Modality-Specific Dose Gradient Modeling for Prostate IMRT Using Spherical Distance Maps of PTV and Isodose Contours. Medical Physics. 2016;43:3653-3654.

    Not in our library10.1118/1.4956999

39. 39.

    Folkerts, M. M. et al. Knowledge-Based Automatic Treatment Planning for Prostate IMRT Using 3-Dimensional Dose Prediction and Threshold-Based Optimization. American Association of Physicists in Medicine (2017).

    Not in our library

40. 40.

    Good D, et al. A knowledge-based approach to improving and homogenizing intensity modulated radiation therapy planning quality among treatment centers: an example application to prostate cancer planning. International Journal of Radiation Oncology* Biology* Physics. 2013;87:176-181.

    Not in our library10.1016/j.ijrobp.2013.03.015

41. 41.

    LeCun Y, et al. Backpropagation applied to handwritten zip code recognition. Neural computation. 1989;1:541-551.

    Not in our library10.1162/neco.1989.1.4.541

42. 42.

    Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 1097–1105 (2012).

    Not in our library

43. 43.

    Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, 580–587 (2014).

    Not in our library

44. 44.

    Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).

    Not in our library

45. 45.

    Long, J., Shelhamer, E. & Darrell, T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431–3440 (2015).

    Not in our library10.1109/tpami.2016.2572683

46. 46.

    Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 234–241 (2015).

    Not in our library

47. 47.

    Noh, H., Hong, S. & Han, B. Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision, 1520–1528 (2015).

    Not in our library

48. 48.

    Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning, 448-456 (2015).

    Not in our library

49. 49.

    Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. Journal of machine learning research. 2014;15:1929-1958.

    Not in our library

50. 50.

    Kingma, D. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).

    Not in our library

51. 51.

    Chollet, F. (Github, https://github.com/fchollet/keras, 2015).

    Not in our library

52. 52.

    Abadi, M. et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).

    Not in our library

53. 53.

    Van’t Riet A, Mak AC, Moerland MA, Elders LH, van der Zee W. A conformation number to quantify the degree of conformality in brachytherapy and external beam irradiation: application to the prostate. International Journal of Radiation Oncology* Biology* Physics. 1997;37:731-736.

    Not in our library10.1016/s0360-3016(96)00601-3

54. 54.

    McIntosh C, Purdie TG. Contextual Atlas Regression Forests: Multiple-Atlas-Based Automated Dose Prediction in Radiation Therapy. IEEE Transactions on Medical Imaging. 2016;35:1000-1012.

    Not in our library10.1109/tmi.2015.2505188

55. 55.

    Milletari, F., Navab, N. & Ahmadi, S.-A. V-net: Fully convolutional neural networks for volumetric medical image segmentation. 3D Vision (3DV), 2016 Fourth International Conference on, 565–571 (2016).

    Not in our library

Cited by papers we hold 2

• Deep learning method for prediction of patient-specific dose distribution in breast cancer · 2021
  Not checked
• Fully automated dose prediction using generative adversarial networks in prostate cancer patients. · 2020
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.