biostudies-literatureChen WPublic Welfare Technology Application Research Project of Lishui CityKey Project of Joint Construction by Provincial and Ministerial Authorities21https://www.ebi.ac.uk/biostudies/studies/S-EPMC12835486biostudies-literatureUnknown17(1)<h4>Objectives</h4>This study was designed to develop a multiregional MRI-based deep learning radiomics nomogram (DLRN) for predicting axillary pathological complete response (apCR) after neoadjuvant chemotherapy (NAC) in breast cancer.<h4>Materials and methods</h4>In total, 539 patients in our hospital were randomly split into a training cohort (TC; n = 431) and an internal validation cohort (IVC; n = 108), and 703 patients were recruited from three external centers as external validation cohorts (EVC1-3). Uni- and multivariate analyses were performed to select clinicopathological characteristics and establish a clinical model. DLR models were constructed based on DL and handcrafted radiomics features extracted from gross tumor volume (GTV) and GTV incorporating 3-, 5-, 7-, and 9-mm peritInsights into imagingMultiregional MRI-based deep learning radiomics to predict axillary response after neoadjuvant chemotherapy in breast cancer patients.PMC12835486WKJ-ZJ-24522024GYX45Xu MChen MLu CXia SJi JZhao TZhou YPeng ZYan ZShi CChen WLin GChen YfalseMultiregional MRI-based deep learning radiomics to predict axillary response after neoadjuvant chemotherapy in breast cancer patients.<h4>Objectives</h4>This study was designed to develop a multiregional MRI-based deep learning radiomics nomogram (DLRN) for predicting axillary pathological complete response (apCR) after neoadjuvant chemotherapy (NAC) in breast cancer.<h4>Materials and methods</h4>In total, 539 patients in our hospital were randomly split into a training cohort (TC; n = 431) and an internal validation cohort (IVC; n = 108), and 703 patients were recruited from three external centers as external validation cohorts (EVC1-3). Uni- and multivariate analyses were performed to select clinicopathological characteristics and establish a clinical model. DLR models were constructed based on DL and handcrafted radiomics features extracted from gross tumor volume (GTV) and GTV incorporating 3-, 5-, 7-, and 9-mm perit2026-01-01T00:00:00Z2026 Jan2026-06-15T08:52:43.814Z2026-06-15T03:11:35.556ZS-EPMC128354864158696310.1186/s13244-025-02193-1