Predicting necessity of daily online adaptive replanning based on wavelet image features for MRI guided adaptive radiation therapy

•A method to determine the necessity of OLAR during MRgART.•A framework to extract wavelet multiscale features from daily MRI during MRgART.•A machine learning classifier to determine when OLAR is beneficial during MRgART. Online adaptive replanning (OLAR) is generally labor-intensive and time-consuming during MRI-guided adaptive radiation therapy (MRgART). This work aims to develop a method to determine OLAR necessity during MRgART. A machine learning classifier was developed to predict OLAR necessity based on wavelet multiscale texture features extracted from daily MRIs and was trained and tested with data from 119 daily MRI datasets acquired during MRgART for 24 pancreatic cancer patients treated on a 1.5 T MR-Linac. Spearman correlations, interclass correlation (ICC), coefficient of variance (COV), t-test (p