Background: This study investigated alternative, non-invasive methods for human papillomavirus (HPV) detection in head and neck cancers (HNCs). We compared two approaches: analyzing computed tomography (CT) scans with a Deep Learning (DL) model and using radiomic features extracted from CT images with machine learning (ML) models. Methods: Fifty patients with histologically confirmed HNC were included. We first trained a modified ResNet-18 DL model on CT data to predict HPV status. Next, radiomic features were extracted from manually segmented regions of interest near the oropharynx and used to train four ML models (K-Nearest Neighbors, logistic regression, decision tree, random forest) for the same purpose. Results: The CT-based model achieved the highest accuracy (90%) in classifying HPV status. Among the ML models, K-Nearest Neighbors performed best (80% accuracy). Weighted Ensemble methods combining the CT-based model with each ML model resulted in moderate accuracy improvements (70–90%). Conclusions: Our findings suggest that CT scans analyzed by DL models hold promise for non-invasive HPV detection in HNC. Radiomic features, while less accurate in this study, offer a complementary approach. Future research should explore larger datasets and investigate the potential of combining DL and radiomic techniques.

This study aimed to compare the commercial dosimetric software Planet® Dose (version 3.1.1) from DOSIsoft and the open-source toolkit GATE. Dosimetry was performed for six patients receiving 200 mCi of Lutathera® every 8 weeks for four treatment cycles. For the dose calculation with Planet®, SPECT/CT images were acquired at 4, 24, 72 and 192 h post-injection. After the registration of all the time points to T0, the organs of interest (OOIs) were segmented. Time-activity curves were produced and the absorbed dose was calculated using the bi- and tri-exponential fitting methods. Regarding GATE simulations, the SPECT images of the 24 h time point were utilized for the radiopharmaceutical biodistribution in the OOIs and the attenuation maps were produced using the CT images. For liver and spleen, the average relative difference between GATE and Planet® was 9.6% and 11.1% for biexponential and 12.4% and 30.5% for triexponential fitting, respectively. The right and left kidneys showed differences up to 10.7% and 10.4% for the biexponential and up to 60.6% and 11.9% for the triexponential model, respectively. The absorbed dose calculated with GATE, Planet®(bi-exp) and Planet®(tri-exp) was in agreement with the literature. The results of the bi-exponential fitting were similar to the GATE-resulted calculations, while the tri-exponential fitting had a higher relative difference.