Intra- and peritumoral MRI radiomics assisted in predicting radiochemotherapy response in metastatic cervical lymph nodes of nasopharyngeal cancer.

ABSTRACT:

Background

To establish and validate radiomic models combining intratumoral (Intra) and peritumoral (Peri) features obtained from pretreatment MRI for the prediction of treatment response of lymph node metastasis from nasopharyngeal cancer (NPC).

Methods

One hundred forty-five NPC patients (102 in the training and 43 in the validation set) were retrospectively enrolled. Radiomic features were extracted from Intra and Peri regions on the metastatic cervical lymph node, and selected with the least absolute shrinkage and selection operator (LASSO). Multivariate logistic regression analysis was applied to build radiomic models. Sensitivity, specificity, accuracy, and the area under the curve (AUC) of receiver operating characteristics were employed to evaluate the predictive pow

SUBMITTER: Xu H 

PROVIDER: S-EPMC10230802 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature