ESTRO 2023 - Abstract Book

S128

Saturday 13 May

ESTRO 2023

inter-observer variability and include peritumoral regions with low probability values. The hypothesis we would like to test in this study is whether using PM instead of GTVp delineations as extra input channel for DL improves the predictive power of CT- and PET-based prediction models for oropharyngeal cancer (OPC) patients for local control (LC), regional control (RC), DMFS and OS . Materials and Methods We included 399 OPC patients from our institute that were treated with (chemo)radiation between 2010 and 2021. For each patient CT and PET images and GTVp contours, used for radiotherapy treatment planning, were collected. We trained a previously developed 2.5D DL framework for tumour probability prediction by 5-fold cross validation using patients from 2019 onwards. Patients treated between 2010 and 2019 were used to train (168) and test (100) the DL model for outcome prediction with the previously mentioned 3D PM as one of the possible inputs. The predictive endpoints were LC, RC, DMFS and OS. The 3D ResNet18 was trained by 3-fold cross validation for each endpoint using different combinations of image modalities as input (see Figure 1). Then, the predictions of these three models were ensembled averaged in the test set. The C-index was used to evaluate the discriminative performance of the models.

•

Results Table 1 shows that the models trained replacing the GTVp contours with the PM achieved highest C-indexes in LC (N° 5), RC (N° 3) and DMFS (N° 3) prediction, which may be due to the presence of low predicted probabilities in the lymph nodes and peritumoral regions in the PM. For OS, adding the PM (N° 3) or the GTVp (N° 4) to the PET resulted in comparable C indexes Additionally, combing best DL models with clinical features further improved C-indexes to 0.61, 0.80 and 0.81 for RC, DMFS and OS prediction, respectively.

Conclusion Adding predicted tumour probability maps instead of GTVp contours as an additional input channel for DL-based outcome prediction models improved the model performance for all outcome endpoints except for overall survival. PD-0168 Impact of tumor nuclei size variation for post radiotherapy recurrence outcome of GYN patients Y. Zou 1 , M. Lecavalier-Barsoum 2 , M. Pelmus 3 , S. Abbasinejad Enger 4 1 McGill University, Department of Biological & Biomedical Engineering, Montreal, Canada; 2 Jewish General Hospital , Department of Radiation Oncology, Montreal, Canada; 3 McGill University, Department of Pathology, Faculty of Medicine , Montreal, Canada; 4 McGill University, Lady Davis Institute for Medical Research, Jewish General Hospital, Department of Oncology, Montreal, Canada Purpose or Objective Ionizing radiation kills tumor cells or inhibits the cell cycle mainly by damaging DNA in the cell nucleus. Patient-specific dose response may be influenced by inter-patient variation in cell/nucleus . This project investigates the relation between the pre-treatment patient-specific nuclei distribution obtained from digitized histopathology images and tumor recurrence outcomes for gynecological patients treated with radiotherapy. Materials and Methods Thirty-six gynecological cancer patients who underwent a combination of external beam radiotherapy, brachytherapy, and concurrent chemotherapy were included in this analysis, 25% of which experienced post radiotherapy recurrence. Median age at diagnosis was 59.5 years with a median follow-up time of 25.7 months. Patient-specific nuclei and cell spacing