Development and validation of a multimodality radiomics-based nomogram for predicting HER2 expression status in invasive breast cancer - Report - MDSpire

Development and validation of a multimodality radiomics-based nomogram for predicting HER2 expression status in invasive breast cancer

  • By

  • Xianwei Yang

  • Xiaoling Liu

  • Shenghong Wan

  • Yilin Luo

  • Mengjun Shen

  • Xin Liao

  • July 14, 2026

Share

Clinical Report: Creation and assessment of a multimodal radiomics nomogram for forecasting HER2 expression in invasive breast cancer patients

Overview

This study developed a nomogram that integrates multimodal imaging and clinical features to predict HER2 expression status in invasive breast cancer patients.

Background

Breast cancer is the most prevalent malignancy among women, with HER2 expression influencing treatment options. Accurate preoperative assessment of HER2 status is crucial for personalized treatment planning. Traditional methods for determining HER2 status are invasive and may not capture tumor heterogeneity, highlighting the need for non-invasive alternatives.

Data Highlights

ModelTraining AUC (95% CI)Validation AUC (95% CI)
Model_1 (HER2-Positive vs. HER2-Zero)0.742 (0.624–0.860)0.718 (0.594–0.842)
Model_2 (HER2-Positive vs. HER2-Low)0.823 (0.749–0.897)0.778 (0.696–0.861)
Model_3 (HER2-Low vs. HER2-Zero)0.831 (0.747–0.916)0.745 (0.640–0.850)

Key Findings

  • The study included 204 patients with pathologically confirmed invasive breast cancer.
  • Three binary classification models were developed to differentiate HER2 expression states.
  • The combined radiomics model outperformed single-modality models for HER2-positive and HER2-low predictions.
  • No nomogram was developed for HER2-Low vs. HER2-Zero due to lack of significant clinicopathological features.
  • The nomogram integrates imaging features with clinical factors for non-invasive HER2 status evaluation.

Clinical Implications

The multimodal radiomics nomogram offers a non-invasive tool for preoperative evaluation of HER2 expression status.

Conclusion

The developed nomogram provides a non-invasive quantitative tool for preoperative evaluation of HER2 expression status in breast cancer.

Related Resources & Content

  1. Frontiers in Oncology, 2026 -- Multiparametric MRI-based nomogram integrating clinicopathological factors for predicting HER2 expression status in breast cancer
  2. European Radiology, 2023 -- A Dual-Phase Nomogram: A Non-Invasive Resource to Aid Breast Radiologists in Clinical Decision-Making
  3. Frontiers in Endocrinology, 2026 -- A multimodal ultrasound-based model combining tumor radiomics and axillary lymph node morphologic classification for predicting axillary nodal burden in breast cancer
  4. European Radiology, 2022 -- Creation and assessment of a radiomics nomogram utilizing [18F]FDG PET/CT to forecast prognostic risks in patients with pretreatment diffuse large B cell lymphoma
  5. Human Epidermal Growth Factor Receptor 2 Testing in Breast Cancer: ASCO–College of American Pathologists Guideline Update | Journal of Clinical Oncology
  6. Trastuzumab Deruxtecan after Endocrine Therapy in Metastatic Breast Cancer | New England Journal of Medicine
  7. Stratified prediction of HER2 status in breast cancer by integrating intratumoral and peritumoral radiomics from DCE-MRI | BMC Cancer
  8. Human Epidermal Growth Factor Receptor 2 Testing in Breast Cancer: ASCO–College of American Pathologists Guideline Update | Journal of Clinical Oncology
  9. Trastuzumab Deruxtecan after Endocrine Therapy in Metastatic Breast Cancer | New England Journal of Medicine
  10. Stratified prediction of HER2 status in breast cancer by integrating intratumoral and peritumoral radiomics from DCE-MRI | BMC Cancer | Springer Nature Link

Original Source(s)

Related Content