Prediction of sentinel lymph node metastasis in early-stage breast cancer by multi-modal magnetic resonance imaging habitat radiomics analysis
CHEN Yixian
CHEN Wubiao
WU Kangwei
LI Xinhua
ZHANG Na
Abstract：Objective An electromics model for habitat imaging was proposed to predict sentinel lymph node metastasis in early breast cancer.Methods The MRI characteristics of 176 patients in our hospital from August 2016 to November 2022 were collected pretreatment,and whether there was metastasis in the sentinel lymph nodes was confirmed by pathological biopsy.Multiple sequences of MRI of the breast tumor region pretreatment were used for habitat imaging in all patients.Results The stepwise multivariate analysis results indicated that the factors associated with sentinel lymph node metastasis include vascular invasion and spiculation(P<0.05).With K=3 as the optimal number of clusters,the region of interest was divided into three subregions for the extraction of radiomics features to construct a habitat model.The habitat prediction model outperformed the single-modality radiomics prediction model in both the training cohort(AUC=0.876,95%CI:0.815-0.938)and the validation cohort(AUC=0.824,95%CI:0.683-0.964).The clinical nomogram constructed by combining clinical risk factors with habitat radiomics demonstrated superior performance in the training cohort(AUC=0.920,95%CI:0.875-0.965)and the validation cohort(AUC=0.908,95%CI:0.810-1.000).Conclusion The radiomics-based habitat nomogram shows outstanding diagnostic effectiveness and has the potential to act as a valuable auxiliary tool for preoperative assessment of sentinel lymph node metastasis in patients with breast cancer.
Keywords：early breast cancermagnetic resonance imaginghabitat imaging
Publication Date：2025-04-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 492-501 )