ESTRO 2023 - Abstract Book

S676

Monday 15 May 2023

ESTRO 2023

Conclusion The proposed cross-entropy based objective functions are a promising tool for restoring a planned dose on a daily anatomy. They can be integrated in an automated online adaptive replanning workflow and used to mitigate dose degradation effects from variations in patient geometry. MO-0804 Is more and bigger also better? Impact of dataset and model size in deep learning dose prediction J. van Genderingen 1 , D. Nguyen 2 , F. Knuth 1 , H. Nomair 1 , L. Incrocci 1 , A. Sharfo 1 , U. Oelfke 3 , S. Jiang 4 , L. Rossi 1 , B. Heijmen 1 , S. Breedveld 1 1 Erasmus MC Cancer Institute, University Medical Center Rotterdam, Department of Radiotherapy, Rotterdam, The Netherlands; 2 UT Southwestern Medical Center, Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, Dallas, USA; 3 The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, Joint Department of Physics, London, United Kingdom; 4 UT Southwestern Medical Center, Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology , Dallas, USA Purpose or Objective Deep learning (DL) has demonstrated to be able to predict realistic 3D dose distributions. In this study, we investigate the impact of dataset and model on the quality of predicted dose distributions. Materials and Methods The 745 included prostate cancer patients from the randomized HYpofractionated irradiation for PROstate cancer (HYPRO) trial were a mix of only prostate, prostate&vesicles (low dose to vesicles) and prostate&vesicles (high dose to vesicles). The patients were split into train/validation/test sets with n=561/75/109 In-house developed Hierarchically Dense U-Net (HDU) networks with 1.1 (HDUsmall) and with 3 (HDUlarge) million trainable parameters were trained for dose prediction. Both HDUs were trained with different subsets of the training set, n=56/140/280/561 (10/25/50/100% of total). CT images with contours of PTVHigh, PTVLow, rectum, bladder, anus and femoral heads were used as input for the prediction models. The ground truth (GT) 23-beam IMRT plans were consistently generated with our in-house system for automated multi-criteria treatment planning, with 78 Gy prescribed dose to PTVHigh and 72.2 Gy to PTVLow. A 23-beam IMRT setup was used to avoid dosimetric bias from few-beam plans or VMAT segmentation. The input dimensions were resampled to 256x256x64, reflecting a resolution of 1.92x1.65x4.66 mm3. The training was performed for 200 epochs on a 48 GB NVIDIA RTX 8000 GPU. HDUlarge was the largest model that could fit on the GPU.

Both for predictions and GT, all doses were normalized to PTVHigh V95%=99%. All dosimetric comparisons between prediction models and GT were performed with same set of test patients.

Results