Abstract
Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.
P. Fischer and H. Willms—Contributed equally.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The code is available at https://github.com/paulkogni/SG-RCPS.
References
Angelopoulos, A.N., et al.: Image-to-image regression with distribution-free uncertainty quantification and applications in imaging. In: International Conference on Machine Learning, pp. 717–730. PMLR (2022)
Bates, S., Angelopoulos, A., Lei, L., Malik, J., Jordan, M.: Distribution-free, risk-controlling prediction sets. J. ACM (JACM) 68(6), 1–34 (2021)
Baumgartner, C.F., et al.: PHiSeg: capturing uncertainty in medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 119–127. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_14
Bol, G., Hissoiny, S., Lagendijk, J., Raaymakers, B.: Fast online monte carlo-based imrt planning for the mri linear accelerator. Phys. Med. Biol. 57(5), 1375 (2012)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Fischer, P., Thomas, K., Baumgartner, C.F.: Uncertainty estimation and propagation in accelerated mri reconstruction. In: Sudre, C.H., Baumgartner, C.F., Dalca, A., Mehta, R., Qin, C., Wells, W.M. (eds.) UNSURE 2023. LNCS, pp. 84–94. Springer, Heidelberg (2023). https://doi.org/10.1007/978-3-031-44336-7_9
Friedel, M., Nachbar, M., Mönnich, D., Dohm, O., Thorwarth, D.: Development and validation of a 1.5 t mr-linac full accelerator head and cryostat model for monte carlo dose simulations. Med. Phys. 46(11), 5304–5313 (2019)
Hall, W., et al.: Mr linac atlantic consortium and the viewray c2t2 research consortium. the transformation of radiation oncology using real-time magnetic resonance guidance: a review. Eur. J. Cancer 122, 42–52 (2019)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. In: The Collected Works of Wassily Hoeffding, pp. 409–426 (1994)
Kawrakow, I., Rogers, D., Mainegra-Hing, E., Tessier, F., Townson, R., Walters, B.: Egsnrc toolkit for monte carlo simulation of ionizing radiation transport (2000). https://doi.org/10.4224/40001303
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)
Kohl, S., et al.: A probabilistic u-net for segmentation of ambiguous images. Adv. Neural Inf. Process. Syst. 31 (2018)
Kontaxis, C., Bol, G., Lagendijk, J., Raaymakers, B.: Deepdose: towards a fast dose calculation engine for radiation therapy using deep learning. Phys. Med. Biol. 65(7), 075013 (2020)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. Adv. Neural Inf. Process. Syst. 30 (2017)
Martinot, S., Bus, N., Vakalopoulou, M., Robert, C., Deutsch, E., Paragios, N.: High-particle simulation of Monte-Carlo dose distribution with 3D ConvLSTMs. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 499–508. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87202-1_48
Neishabouri, A., Wahl, N., Mairani, A., Köthe, U., Bangert, M.: Long short-term memory networks for proton dose calculation in highly heterogeneous tissues. Med. Phys. 48(4), 1893–1908 (2021)
Randall, J.W., Rammohan, N., Das, I.J., Yadav, P.: Towards accurate and precise image-guided radiotherapy: clinical applications of the mr-linac. J. Clin. Med. 11(14), 4044 (2022)
Tsekas, G., Bol, G., Raaymakers, B., Kontaxis, C.: Deepdose: a robust deep learning-based dose engine for abdominal tumours in a 1.5 t mri radiotherapy system. Phys. Med. Biol. 66(6), 065017 (2021)
Acknowledgments
This work was supported by the Excellence Cluster 2064 “Machine Learning—New Perspectives for Science”, project number 390727645 and received funding from the German Research Council under DFG Grant No. ZI 736/2-1. The authors thank the International Max Planck Research School for Intelligent Systems (IMPRS-IS) for supporting Paul Fischer. The authors acknowledge support by the state of Baden-Württemberg through bwHPC (INST39/963-1 FUGG bwForCluster NEMO) and through the Research and Training Network “AI4MedBW”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
The authors have no competing interests to declare.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fischer, P., Willms, H., Schneider, M., Thorwarth, D., Muehlebach, M., Baumgartner, C.F. (2024). Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science, vol 15010. Springer, Cham. https://doi.org/10.1007/978-3-031-72117-5_65
Download citation
DOI: https://doi.org/10.1007/978-3-031-72117-5_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72116-8
Online ISBN: 978-3-031-72117-5
eBook Packages: Computer ScienceComputer Science (R0)
