LAUSR

Simple Summary This study developed a deep learning model to predict treatment outcomes in pharyngeal cancer patients undergoing radiotherapy. We analyzed 162 patients with oropharyngeal or hypopharyngeal cancer who received definitive radiotherapy between 2008 and 2020. The model utilizes both baseline and adaptive radiation therapy (ART) simulation CT images to forecast the risk of local recurrence, nodal relapse, and distant metastasis. Using a deep contrastive learning framework with a merged ensemble approach, the model achieved area under the curve values of 0.773, 0.747, and 0.793 for predicting these three endpoints, respectively, with corresponding accuracies of 72.4%, 74.7%, and 75.7%. While these results demonstrate promising predictive capability, external validation with multi-center datasets is essential to confirm the model’s generalizability and robustness across different patient populations and imaging protocols. Abstract Background/Objectives: The implementation of adaptive radiation therapy (ART) is increasingly becoming widely available in the clinical practice of radiotherapy (RT). For patients with pharyngeal cancer receiving RT, this study aimed to develop a deep learning (DL) model by merging baseline and ART simulation computed tomography (CT) images to predict treatment outcomes. Methods: Clinical and imaging data from 162 patients of newly diagnosed oropharyngeal or hypopharyngeal cancer were analyzed. All completed definitive treatment and their baseline and ART non-contrast simulation CTs were utilized for training. After augmentation of the CT images, a deep contrastive learning model was employed to predict the occurrence of local recurrence (LR), neck lymph node relapse (NR), and distant metastases (DM). Receiver operating characteristic curve analysis was conducted to evaluate the model’s performance. Results: Over a median follow-up period of 34 months, 53 (32.7%), 36 (22.2%), and 23 (14.0%) patients developed LR, NR, and DM, respectively. Following the integration of prediction results from baseline and ART simulation CTs, the area under the curve for predicting the occurrence of LR, NR, and DM reached 0.773, 0.747, and 0.793. At the same time, the accuracy for the three endpoints was 72.4%, 74.7%, and 75.7%, respectively. Conclusions: For patients with pharyngeal cancer ready to receive RT-based treatment, our proposed models can predict the development of LR, NR, or DM through baseline and ART simulation CTs. External validation needs to be conducted to confirm the model’s performance.