ESTRO 2022 - Abstract Book

S134

Abstract book

ESTRO 2022

Conclusion This study confirmed ERI as a good biomarker also in case of LACC, with higher performance in DW images. In particular, the high value of specificity of ERI_DWI demonstrates high reliability in early identifying patients who will not go through a complete response, so allowing to the clinicians to modify the treatment approach in time. An external validation study is required before to implement such biomarker in clinical practice

PD-0159 Deep learning and radiomics of PET/CT images for head and neck cancer treatment outcome prediction

B.N. Huynh 1 , A.R. Groendahl 1 , S.E.R. Langberg 2 , O. Tomic 1 , E. Malinen 3,4 , E. Dale 5 , C.M. Futsaether 1

1 Norwegian University of Life Sciences, Faculty of Science and Technology, Ås, Norway; 2 Cancer Registry of Norway, Department of Registry Informatics, Oslo, Norway; 3 Oslo University Hospital, Department of Medical Physics, Oslo, Norway; 4 University of Oslo, Department of Physics, Oslo, Norway; 5 Oslo University Hospital, Department of Oncology, Oslo, Norway Purpose or Objective Deep learning models were used to elucidate the roles of clinical factors and radiomics features for predicting disease free survival (DFS), loco-regional control (LRC) and overall survival (OS) in head and neck cancer (HNC) patients. Materials and Methods 139 HNC patients with an 18F-FDG PET/CT scan acquired before radiotherapy were included. The input data consisted of 11 clinical factors, 3 PET parameters (SUV peak , MTV, TLG) and 468 IBSI-listed radiomics features extracted from the primary tumor volume in the PET and CT images. All numeric features were preprocessed using z-score normalization. Three different groups of input data were used to tune separate fully connected deep learning architectures (Fig. 1a, Table 1 models M1-M3): Input data 1 (D1) 11 clinical factors; Input data 2 (D2) 3 PET parameters, 60 1 st order statistical & shape features; Input data 3 (D3) 408 textural features. D2 and D3 were defined as radiomics features. A dropout layer, which randomly deactivated 25% of the nodes, was added to the end of each architecture to prevent overfitting. The prediction targets DFS, LRC and OS were treated as binary responses. Local or regional failure was counted as an LRC event, whereas DFS also included metastatic disease or death as a DFS event. Deep learning architectures designed separately for D1, D2 and D3 (Fig. 1a), were then concatenated in the second last layer, creating four additional models (Table 1 M4-M7) with multiple input paths (Fig. 1b) trained on input data D1 & D2, D1 & D3, D2 & D3 and D1 & D2 & D3. Ensembles (Table 1 M8-M12, Fig. 1c) based on the mean predicted class probability of models M1-M3 and M6 were also evaluated. All models were trained using five-fold cross-validation, where the folds were stratified to conserve the proportion of stage I+II vs. III+IV patients (8 th edition AJCC/UICC) in the full dataset. The Area Under the Receiver Operating Characteristic Curve (ROC-AUC) was used to evaluate model performance.