Background
We sought to investigate the prognostic value of volumetric positron emission tomography (PET) parameters in patients with human papillomavirus (HPV)‐related oropharyngeal squamous cell carcinoma (OPSCC) and a ≤10 pack‐year smoking history treated with chemoradiation.
Methods
A total of 142 patients were included. Maximum standardized uptake value, metabolic tumor volume, and total lesion glycolysis (TLG) of the primary tumor, involved regional lymph nodes, and total lesion were calculated. Cox proportional hazard modeling was used to evaluate associations of clinical and PET parameters with locoregional failure‐free survival (LRFFS), distant metastasis‐free survival (DMFS), and overall survival (OS).
Results
On univariate analysis, volumetric PET parameters were significantly associated with all endpoints, and 8th edition American Joint Committee on Cancer/Union Internationale Contre le Cancer staging was significantly associated with DMFS and OS. On multivariate analysis, total lesion TLG was significantly associated with LRFFS, while staging was most significantly prognostic for DMFS and OS.
Conclusion
Volumetric PET parameters are uniquely prognostic of LRFFS in low‐risk HPV‐related OPSCC and may be useful for directing de‐intensification strategies.
A B S T R A C TBackground and purpose: Computed tomography (CT) radiomics of head and neck cancer (HNC) images is susceptible to dental implant artifacts. This work devised and validated an automated algorithm to detect CT metal artifacts and investigate their impact on subsequent radiomics analyses. A new method based on features from total variation, gradient directional distribution, and Hough transform was developed and evaluated. Materials and methods: Two HNC datasets were analyzed: a training set of 131 patients for developing the detection algorithm and a testing set of 220 patients. Seven designated features were extracted from ROIs (regions of interest) and machine learning with random forests was used for building the artifact detection algorithm. Performance was assessed using the area under the receiver operating characteristics curve (AUC). Results: The testing results of artifacts detection yielded a cross-validated AUC of 0.91 (95% CI: 0.89-0.94), and a test AUC of 0.89. External testing validation yielded an accuracy of 0.82. For radiomics model prediction, training with artifacts yielded an AUC of 0.64 (95% CI: 0.63-0.65), while training on images without artifacts improved the AUC to 0.75 (95% CI: 0.74-0.76). This was compared to visual inspection of artifacts (AUC = 0.71 [95% CI: 0.69-0.73]). Conclusion: We developed a new method for automated and efficient detection of streak artifacts. We also showed that such streak artifacts in HNC CT images can worsen the performance of radiomics modeling.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.