Enhancing Predictive Accuracy for Recurrence-Free Survival in Head and Neck Tumor: A Comparative Study of Weighted Fusion Radiomic Analysis

Abstract

Despite advancements in oncology, predicting recurrence-free survival (RFS) in head and neck (H&N) cancer remains challenging due to the heterogeneity of tumor biology and treatment responses. This study aims to address the research gap in the prognostic efficacy of traditional clinical predictors versus advanced radiomics features and to explore the potential of weighted fusion techniques for enhancing RFS prediction. We utilized clinical data, radiomic features from CT and PET scans, and various weighted fusion algorithms to stratify patients into low- and high-risk groups for RFS. The predictive performance of each model was evaluated using Kaplan-Meier survival analysis, and the significance of differences in RFS rates was assessed using confidence interval (CI) tests. The weighted fusion model with a 90% emphasis on PET features significantly outperformed individual modalities, yielding the highest C-index. Additionally, the incorporation of contextual information by varying peritumoral radii did not substantially improve prediction accuracy. While the clinical model and the radiomics model, individually, did not achieve statistical significance in survival differentiation, the combined feature set showed improved performance. The integration of radiomic features with clinical data through weighted fusion algorithms enhances the predictive accuracy of RFS outcomes in head and neck cancer. Our findings suggest that the utilization of multi-modal data helps in developing more reliable predictive models and underscore the potential of PET imaging in refining prognostic assessments. This study propels the discussion forward, indicating a pivotal step toward the adoption of precision medicine in cancer care.

Keywords: head and neck cancer; predictive modeling; radiomics; recurrence-free survival; weighted fusion.

Figure 1

2D sagittal slices of fused PET/CT images from each of the nine participating centers.

Figure 2

The comprehensive methodology of the Weighted Fusion Bag of ML Algorithms for dual PET/CT imaging in predicting head and neck tumor outcomes.

Figure 3

Comparison of metrics across different imaging modalities.

Figure 4

Comparison of metrics across a combination of various imaging modalities.

Figure 5

A graphical representation comparing RFS prediction across three lesion types: Primary Tumor, Lymph Node Lesions, and Combined Lesions.

Figure 6

Comparative analysis of RFS prediction across various contextual distances (r = 0 to r = 100) from the tumor boundary, evaluating the impact of incorporating peritumoral tissue characteristics into the predictive modeling process.

Figure 7

Comparison of RFS prediction accuracy using different feature sets: Clinical, Radiomics, and Combined.

Figure 8

Kaplan–Meier survival curves for RFS across different model approaches. (a) Image-level feature fusion, (b) feature-level feature fusion, (c) CT modality alone, (d) PET modality alone, (e) clinical model, and (f) combined clinical and radiomics model. The p-values indicate the statistical significance of the differences between the low-risk and high-risk groups.