Abstract
Deep learning-based image segmentation for radiotherapy is intended to speed up the planning process and yield consistent results. However, most of these segmentation methods solely rely on distribution and geometry-associated training objectives without considering tumor control and the sparing of healthy tissues. To incorporate dosimetric effects into segmentation models, we propose a new training loss function that extends current state-of-the-art segmentation model training via a dose-based guidance method. We hypothesized that adding such a dose-guidance mechanism improves the robustness of the segmentation with respect to the dose (i.e., resolves distant outliers and focuses on locations of high dose/dose gradient). We demonstrate the effectiveness of the proposed method on Gross Tumor Volume segmentation for glioblastoma treatment. The obtained dosimetry-based results show reduced dose errors relative to the ground truth dose map using the proposed dosimetry-segmentation guidance, outperforming state-of-the-art distribution and geometry-based segmentation losses.
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.
Code available under https://github.com/ruefene/doselo.
References
Bakas, S., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629 (2018)
Cloak, K., et al.: Contour variation is a primary source of error when delivering post prostatectomy radiotherapy: results of the trans-tasman radiation oncology group 08.03 radiotherapy adjuvant versus early salvage (raves) benchmarking exercise. J. Med. Imag. Radiat. Oncol. 63(3), 390–398 (2019)
Dayani, F., et al.: Safety and outcomes of resection of butterfly glioblastoma. Neurosurg. Focus 44(6), E4 (2018)
Fidon, L., et al.: A dempster-shafer approach to trustworthy AI with application to fetal brain MRI segmentation. arXiv preprint arXiv:2204.02779 (2022)
Galdran, A., Carneiro, G., Ballester, M.A.G.: On the optimal combination of cross-entropy and soft dice losses for lesion segmentation with out-of-distribution robustness. In: Yap, M.H., Kendrick, C., Cassidy, B. (eds.) Diabetic Foot Ulcers Grand Challenge. DFUC 2022. LNCS, vol. 13797. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-26354-5_4
Gneiting, T., Raftery, A.E.: Strictly proper scoring rules, prediction, and estimation. J. Am. Stat. Assoc. 102(477), 359–378 (2007)
Guo, C., Huang, P., Li, Y., Dai, J.: Accurate method for evaluating the duration of the entire radiotherapy process. J. Appl. Clin. Med. Phys. 21(9), 252–258 (2020)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Kamath, A., Poel, R., Willmann, J., Andratschke, N., Reyes, M.: How sensitive are deep learning based radiotherapy dose prediction models to variability in organs at risk segmentation? In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1–4. IEEE (2023)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kofler, F., et al.: Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the dice coefficient. arXiv preprint arXiv:2103.06205 (2021)
Liu, S., Zhang, J., Li, T., Yan, H., Liu, J.: A cascade 3D U-Net for dose prediction in radiotherapy. Med. Phys. 48(9), 5574–5582 (2021)
Ma, J., et al.: Loss odyssey in medical image segmentation. Med. Image Anal. 71, 102035 (2021)
Mehrtash, A., Wells, W.M., Tempany, C.M., Abolmaesumi, P., Kapur, T.: Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Trans. Med. Imaging 39(12), 3868–3878 (2020). https://doi.org/10.1109/TMI.2020.3006437
Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D vision (3DV), pp. 565–571. IEEE (2016)
Niyazi, M., et al.: ESTRO-ACROP guideline “target delineation of glioblastomas.” Radiotherapy Oncol. 118(1), 35–42 (2016)
Poel, R., et al.: Impact of random outliers in auto-segmented targets on radiotherapy treatment plans for glioblastoma. Radiat. Oncol. 17(1), 170 (2022)
Poel, R., et al.: The predictive value of segmentation metrics on dosimetry in organs at risk of the brain. Med. Image Anal. 73, 102161 (2021)
Reinke, A., et al.: Common limitations of performance metrics in biomedical image analysis. In: Medical Imaging with Deep Learning (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Scoccianti, S., et al.: Organs at risk in the brain and their dose-constraints in adults and in children: a radiation oncologist’s guide for delineation in everyday practice. Radiother. Oncol. 114(2), 230–238 (2015)
Vaassen, F., et al.: Evaluation of measures for assessing time-saving of automatic organ-at-risk segmentation in radiotherapy. Phys. Imag. Radiat. Oncol. 13, 1–6 (2020)
Vandewinckele, L., et al.: Overview of artificial intelligence-based applications in radiotherapy: recommendations for implementation and quality assurance. Radiother. Oncol. 153, 55–66 (2020)
Vinod, S.K., Jameson, M.G., Min, M., Holloway, L.C.: Uncertainties in volume delineation in radiation oncology: a systematic review and recommendations for future studies. Radiother. Oncol. 121(2), 169–179 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rüfenacht, E. et al. (2023). Dose Guidance for Radiotherapy-Oriented Deep Learning Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14228. Springer, Cham. https://doi.org/10.1007/978-3-031-43996-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-031-43996-4_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43995-7
Online ISBN: 978-3-031-43996-4
eBook Packages: Computer ScienceComputer Science (R0)
