Predicting poor response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer: Model constructed using pre-treatment MRI features of structured report template

•A nomogram was developed incorporating the pre-treatment MRI features of the structured report template and clinical factors to predict poor responses in patients with LARC after neoCRT.•The nomogram showed good discrimination as well as good calibration in both the training and test datasets.•Our model performed better than the models including the TNM stage and clinical factors.•This nomogram has the potential for application as a convenient and non-invasive tool for clinicians to preoperatively estimate LARC patients’ risk of poor responses to neoCRT.