Integrating intratumoral and peritumoral radiomics with deep transfer learning from multiparametric MRI for preoperative prediction of HER2 status in breast cancer: a multicenter study - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Combining Intratumoral and Peritumoral Radiomics with Deep Transfer Learning from Multiparametric MRI for Preoperative Assessment of HER2 Status in Breast Cancer: A Multicenter Investigation

  • By

  • Saisai Zhang

  • Jing Rong

  • Tiantian Liu

  • Xiujuan Yin

  • Shuqin Xue

  • Likang Yin

  • Lei Liu

  • Yang Ji

  • Xijun Gong

  • Xiao Wang

  • August 28, 2026

Share

  • 1

    The study assessed a model combining clinical indicators with radiomics and deep transfer learning for predicting HER2 status in breast cancer.

  • 2

    Data from 411 breast cancer patients across three centers were used, with cohorts for training, internal validation, and external testing.

  • 3

    The combined model achieved AUCs of 0.965 in the training cohort and 0.904 in the internal validation cohort for HER2 status prediction.

  • 4

    External test sets demonstrated AUCs of 0.844 and 0.846, indicating the model's predictive performance across different populations.

  • 5

    The model integrates intratumoral and peritumoral features from multiparametric MRI, enhancing the accuracy of HER2 status assessment.

Original Source(s)

Integrating intratumoral and peritumoral radiomics with deep transfer learning from multiparametric MRI for preoperative prediction of HER2 status in breast cancer: a multicenter study

  • by Saisai Zhang, Jing Rong, Tiantian Liu, Xiujuan Yin, Shuqin Xue, Likang Yin, Lei Liu, Yang Ji, Xijun Gong, Xiao Wang

  • August 28, 2026

Related Content

Retraction Note: Long non-coding RNA BRE-AS1 inhibits the proliferation, migration, and invasion of cancer cells in triple-negative breast cancer and predicts patients’ survival by downregulating miR-21

A machine learning-based prognostic model for de novo metastatic HR-positive breast cancer: SEER cohort with external validation

Efficacy and safety analysis of immune checkpoint inhibitors combined with chemotherapy in the treatment of advanced triple-negative breast cancer: an umbrella meta-analysis