No abstract

achieved when Radiomics was used alone. The combination of Radiomics with addiction provided better AUC of 0.86 and accuracy of 88%. Accuracy for T staging was 60 % with AUC 0.81, while for recurrence combination of Radiomics, baseline ADC values and clinical addiction gave us best model with accuracy of 81%, AUC 0.76 and kappa of 0.45. (Details in table) Conclusion: The study is an effort to bridge the unmet need of translational predictive biomarkers in stratification of HPV positive OPSCC patients based on prognosis value. Radiomics features on imaging could be vital in deciphering molecular phenotypes, serve as tools for prognostication and predict recurrence.

The diagnosis of the presence of metastatic lymph nodes from abdominal computed tomography (CT) scans is an essential task performed by radiologists to guide radiation and chemotherapy treatment. State-of-the-art deep learning classifiers trained for this task usually rely on a training set containing CT volumes and their respective image-level (i.e., global) annotation. However, the lack of annotations for the localisation of the regions of interest (ROIs) containing lymph nodes can limit classification accuracy due to the small size of the relevant ROIs in this problem. The use of lymph node ROIs together with global annotations in a multi-task training process has the potential to improve classification accuracy, but the high cost involved in obtaining the ROI annotation for the same samples that have global annotations is a roadblock for this alternative. We address this limitation by introducing a new training strategy from two data sets: one containing the global annotations, and another (publicly available) containing only the lymph node ROI localisation. We term our new strategy semisupervised multi-domain multi-task training, where the goal is to improve the diagnosis accuracy on the globally annotated data set by incorporating the ROI annotations from a different domain. Using a private data set containing global annotations and a public data set containing lymph node ROI localisation, we show that our proposed training mechanism improves the area under the ROC curve for the classification task compared to several training method baselines.