Predictive quantitative ultrasound radiomic markers associated with treatment response in head and neck cancer

Aim: We aimed to identify quantitative ultrasound (QUS)-radiomic markers to predict radiotherapy response in metastatic lymph nodes of head and neck cancer. Materials & methods: Node-positive head and neck cancer patients underwent pretreatment QUS imaging of their metastatic lymph nodes. Imaging features were extracted using the QUS spectral form, and second-order texture parameters. Machine-learning classifiers were used for predictive modeling, which included a logistic regression, naive Bayes, and k-nearest neighbor classifiers. Results: There was a statistically significant difference in the pretreatment QUS-radiomic parameters between radiological complete responders versus partial responders (p < 0.05). The univariable model that demonstrated the greatest classification accuracy included: spectral intercept (SI)-contrast (area under the curve = 0.741). Multivariable models were also computed and showed that the SI-contrast + SI-homogeneity demonstrated an area under the curve = 0.870. The three-feature model demonstrated that the spectral slope-correlation + SI-contrast + SI-homogeneity-predicted response with accuracy of 87.5%. Conclusion: Multivariable QUS-radiomic features of metastatic lymph nodes can predict treatment response a priori. Lay abstract: In this study, quantitative ultrasound (QUS) and machine-learning classification was used to predict treatment outcomes in head and neck cancer patients. Metastatic lymph nodes in the neck were scanned using conventional frequency ultrasound (US). Quantitative data were collected from the US-radiofrequency signal a priori. Machine-learning classification models were computed using QUS features; these included the linear fit parameters of the power spectrum, and second-order texture parameters of the QUS parametric images. Treatment outcomes were measured based on radiological response. Patients were classified into binary groups: radiologic complete response (CR) or radiological partial response (PR), which was assessed 3 months following treatment. Initial results demonstrate high accuracy (%Acc = 87.5%) for predicting radiological response. The results of this study suggest that QUS can be used to predict head and neck cancer response to radiotherapy a priori.