ESTRO 2024 - Abstract Book

S4422

Physics - Machine learning models and clinical applications

ESTRO 2024

Figure 2: Ground truth vs predicted dose metrics for DL strategy (3). Each marker represents a predicted dose parameter with the corresponding ground truth value for one scenario of one the 78 test patients. Marker colours refer to investigated scenarios.

Keywords: robust IMPT,scenairo dose prediction,deep learning

References:

[1] Breedveld, S., Storchi, P.R.M., Voet, P.W.J. and Heijmen, B.J.M. (2012), iCycle: Integrated, multicriterial beam angle, and profile optimization for generation of coplanar and noncoplanar IMRT plans. Med. Phys., 39: 951-963. https://doi.org/10.1118/1.3676689 [2] van de Water, S., Kraan, A. C., Breedveld, S., Schillemans, W., Teguh, D. N., Kooy, H. M., ... & Hoogeman, M. S. (2013). Improved efficiency of multi-criteria IMPT treatment planning using iterative resampling of randomly placed pencil beams. Physics in Medicine & Biology, 58(19), 6969. https://doi.org/10.1088/0031-9155/58/19/6969