Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer - Takeaways - MDSpire

Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer

  • By

  • Bo Xie

  • Xue Peng

  • Yueyan Wang

  • Xinyuan Wen

  • Yindi Hu

  • Yihan Li

  • Xinnan You

  • Yichuan Ma

  • May 18, 2026

  • 0 min

Share

  • 1

    The study developed a habitat radiomics model using mpMRI to enhance preoperative prediction of axillary lymph node metastasis in triple-negative breast cancer.

  • 2

    125 patients with confirmed TNBC underwent mpMRI, with tumors segmented and analyzed for intratumoral heterogeneity using an unsupervised clustering approach.

  • 3

    The combined model, integrating clinical data and habitat radiomics, achieved the highest AUC of 0.81 in predicting axillary lymph node metastasis.

  • 4

    SHAP analysis identified axillary lymph node length as the most significant predictor in the test set, underscoring the model's interpretability.

  • 5

    The habitat radiomics model outperformed conventional radiomics, highlighting the importance of intratumoral heterogeneity in non-invasive nodal risk assessment.

Original Source(s)

Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer

  • by Bo Xie, Xue Peng, Yueyan Wang, Xinyuan Wen, Yindi Hu, Yihan Li, Xinnan You, Yichuan Ma

  • May 18, 2026

Related Content

Dynamic changes and clinical significance of the gut microbiota and serum metabolites in breast cancer onset, progression and chemotherapy intervention

Recent advances in dissolving microneedles for breast cancer immunotherapy: local delivery and tumor microenvironment remodeling

Correction: Regulatory actions of LH and follicle-stimulating hormone on breast cancer cells and mammary tumors in rats