The Radionics Features Could Be Used to Predict the Distinct Metastases in Nasopharyngeal Carcinoma Patients

Abstract

Objectives For NPC patients, distant metastasis is now the main reason for treatment failure. The patients with distinct metastases need different therapeutic regimen and have distinct prognosis. Radiomics might help us predict the type of metastases effectively. Methods The MRI data of seventy non-metastatic NPC patients who develop distant metastasis within five years after treatment were collected and 4410 radiomics features for each patient were extracted by PyRadiomics. Every radiomics feature were compared among patients with distinct metastases and tested by the receiver operating characteristic curve. Results Twenty features have significant differences between the bone metastases cohort and lung metastases cohort, two features have significant differences between the bone metastases cohort and liver metastases cohort, one feature has significant differences between the bone metastases cohort and multiple metastases cohort and sixty-seven features have significant differences between the lung metastases cohort and liver metastases cohort. Six T2WI features could identified lung metastases from bone metastases and liver metastases effectively (AUC = 0.851 ~ 0.896), two T1WI features and one CE T1WI feature could respectively identified bone metastases from liver metastases and multiple metastases effectively (AUC = 0.779 ~ 0.821). Conclusion The results indicate that the radionics features could reflect some of the characteristics of distinct metastases and have potential to be used as predictor of distinct metastases.