ESTRO 2022 - Abstract Book

S1574

Abstract book

ESTRO 2022

This study has utilised machine learning classification models to assess the predictive ability of a novel radiogenomics signature in prostate cancer disease progression. Radiogenomics models had the greatest predictive ability for BCR in comparison with clinicopathological, radiomics, and gene expression models. The availability of a larger prostate cancer radiation response cohort with more disease progression events in the future could provide a pathway to the identification of a robust radiogenomics prognostic signature.

PO-1770 Prediction of mandibular ORN with DL-based classification of 3D radiation dose distribution maps

L. Humbert-Vidan 1,2 , V. Patel 3 , R. Andlauer 2 , A.P. King 2 , T. Guerrero Urbano 4,5

1 Guy's and St Thomas' NHS Foundation Trust , Radiotherapy Physics , London, United Kingdom; 2 King's College London, School of Biomedical Engineering & Imaging Sciences, London, United Kingdom; 3 Guy's and St Thomas' NHS Foundation Trust, Oral Surgery, London, United Kingdom; 4 Guy's and St Thomas' NHS Foundation Trust, Clinical Oncology, London, United Kingdom; 5 King's College London, Cancer Clinical Academic Group, London, United Kingdom Purpose or Objective Absorbed radiation dose to the mandible is an important risk factor in the development of mandibular ORN in patients with HNC. Dosimetric parameters typically included in ORN risk prediction studies are DVH-based, and localisation information is thus lacking. We propose the use of a binary classification 3D convolutional neural network (CNN) to extract the relevant dosimetric information from mandibular 3D radiation dose distribution maps and predict the incidence of ORN. Materials and Methods A total of 70 ORN cases were retrospectively selected from our clinical database and matched with 70 control cases based on primary tumour site. For the purpose of this study, any grade of ORN was considered an event. The mandibular radiation dose distribution volume was calculated based on the RT plan and mandible structure DICOM files. The 3D DenseNet CNN was implemented for binary classification using the MONAI Pytorch-based framework. A Softmax activation layer was added at the end to obtain the predicted probability for each class. The network was trained on 3D dose distribution volumes for 200 epochs with a dropout rate of 0.8 and a step-decay learning rate schedule of step size 50 and gamma factor 0.5. A class-balanced test dataset was kept aside for inference. Stratified cross validation was applied to the rest of the data for hyper-parameter optimisation. Small 3D random rotation and zoom augmentations were applied to the training images with a batch size of 5. A soft voting ensemble was created with 9 repeats of the final CNN to compensate for model variance in the test class label prediction accuracy results. A hard voting ensemble of 9 random forest (RF) binary classifiers was implemented with mandible DVH-based metrics for comparison to the CNN-based results. Results The 3D CNN was able to predict ORN incidence on the independent test dataset with an ensemble accuracy of 75% (range 71% to 86%). The ensemble accuracy obtained with the RF binary classifier was also 75% (range 75% to 78%). Conclusion Our results support the use of 3D dose distribution maps as an alternative to DVH-based dosimetric variables in ORN prediction models. Clinical decisions such as pre-RT dental extractions or radiation dose reduction would benefit from knowledge about which mandible region is more likely to develop ORN for a particular patient. This study is a first step towards individualised prediction of mandibular ORN localisation probability. A. CARRÉ 1,2 , G. Klausner 1,2 , S. Achkar 1,2 , T. Estienne 2,4 , T. Henry 3 , A. Rouyar 1,2 , R. Sun 1,2 , G. Fournier 1,2 , F. Dhermain 1,2 , E. Deutsch 1,2 , C. Robert 1,2 1 Gustave Roussy Cancer Campus, Department of radiation oncology, Villejuif, France; 2 Université Paris-Saclay, Gustave Roussy Cancer Campus, U1030 Radiothérapie Moléculaire et Innovation Thérapeutique, Villejuif, France; 3 Gustave Roussy Cancer Campus, Department of radiology, Villejuif, France; 4 Université Paris-Saclay, CentraleSupélec, Mathématiques et Informatique pour la Complexité et les Systèmes, Gif-sur-Yvette, France, France Purpose or Objective Glioblastomas (GBM) are the most common primary brain tumors in adults with a high lethality. Recurrences in this tumor histology are mostly local, despite aggressive treatments combining surgery, chemotherapy, and radiotherapy (RT). Today, RT is prescribed using a “one fits all” concept, i.e., the same dose is prescribed in the whole Planning Target Volume without consideration of local tumor aggressiveness. We made the hypothesis that GBM would benefit from voxel-scale dose painting. We thus investigated whether deep-learning models could predict recurrence sites based on post-operative anatomical MR images. Materials and Methods All adult patients treated for a histologically proven GBM between 2008 and 2015 in a single institution using a conventional normofractionated RT scheme within STUPP protocol were included. An additional inclusion criterion was the availability of the following sets of images at both baseline (T Baseline ) and recurrence (T Recurrence ) times: a T1-w axial MRI sequence, a T1- w axial MRI sequence with gadolinium injection, and a T2-w axial FLAIR sequence. Primary surgery consisted of either stereotactic biopsy, subtotal resection, or safe wide resection. In all cases, RT delivered a total dose of 60 Gy in 30 fractions, PO-1771 Prediction of recurrence from post-operative MRI in GBM: Are we reaching limits of Deep-Learning?