Technical note: On the development of an outcome-driven frequency filter for improving radiomics-based modeling of human papillomavirus (HPV) in patients with oropharyngeal squamous cell carcinoma
Recommended Citation
Bagher-Ebadian H, Zhu S, Siddiqui F, Lu M, Movsas B, and Chetty IJ. Technical Note: On the development of an outcome-driven frequency filter for improving Radiomics-based modeling of Human Papilloma Virus (HPV) in patients with oropharyngeal squamous cell carcinomas. Med Phys 2021.
Document Type
Article
Publication Date
8-12-2021
Publication Title
Medical physics
Abstract
PURPOSE: To implement an outcome-driven frequency filter for improving radiomics-based modeling of human papillomavirus (HPV) for patients with oropharyngeal squamous cell carcinoma (OPSCC).
METHODS AND MATERIALS: One hundred twenty-eight OPSCC patients with known HPV status (60-HPV+ and 68-HPV-, confirmed by immunohistochemistry-P16 protein testing) were retrospectively studied. A 3D Discrete Fourier Transform was applied on contrast-enhanced computed tomography (CE-CT) images of patient gross tumor volumes (GTVs) to transform intensity distributions to the frequency domain and estimate frequency power spectrums of HPV- and HPV+ patient cohorts. Statistical analyses were performed to rank frequency bands contributing toward the prediction of HPV status. An outcome-driven frequency filter was designed accordingly and applied to GTV frequency information. A 3D inverse discrete Fourier transform was applied to reconstruct HPV-related frequency-filtered images. Radiomics features (11 feature-categories) were extracted from pre- and post-frequency filtered images using our previously published "ROdiomiX" software. Least-absolute-shrinkage-and-selection-operation (Lasso) combined with a generalized linear model (Lasso-GLM) was developed to identify and rank feature subsets with the optimal information for prediction of HPV+/-. Radiomics-based Lasso-GLM classifiers (pre- and post-frequency filtered) were constructed and validated using random permutation sampling and nested cross-validation (CV) techniques. Average area under the receiver operating characteristic (AUC), and positive and negative predictive values (PPV and NPV) were computed to estimate generalization error and prediction performance.
RESULTS: Among 192 radiomic features, 15 features were found to be statistically significant discriminators between HPV+/- cohorts on post-frequency filtered CE-CT images. Fourteen such radiomic features were observed on pre-frequency filtered datasets. Discriminant features included tumor morphology and intensity contrast. Performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were as follows: AUC/PPV/NPV = 0.789/0.755/0.805 and 0.850/0.808/0.877, respectively. Nested CV performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were as follows: AUC/PPV/NPV = 0.814/0.725/0.877 and 0.890/0.820/0.911, respectively.
CONCLUSION: Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results on the importance of frequency analysis prior to radiomic feature extraction toward enhancement of model performance for characterizing HPV in patients with OPSCC.
PubMed ID
34390003
ePublication
ePub ahead of print
