A deep learning framework to stratify Nottingham histologic grade 2 breast tumors based on dynamic contrast-enhanced MRI - Takeaways - MDSpire

A deep learning framework to stratify Nottingham histologic grade 2 breast tumors based on dynamic contrast-enhanced MRI

  • By

  • Roham Hadidchi

  • Anchita Agrawal

  • Michael Z. Liu

  • Takouhie Maldijan

  • Yihui Zhu

  • Hien Quang Nguyen

  • Jinyu Lu

  • Della Makower

  • Susan Fineberg

  • Tim Q. Duong

  • December 17, 2025

  • 0 min

Share

  • 1

    The Nottingham Histologic Grade (NHG) is a key prognostic factor in breast cancer, influencing treatment decisions based on tumor differentiation.

  • 2

    NHG2 tumors, which comprise half of breast cancer cases, exhibit diverse biological behaviors and clinical outcomes, complicating treatment strategies.

  • 3

    Deep learning models utilizing dynamic contrast-enhanced MRI (DCE MRI) can enhance risk stratification for NHG2 tumors, improving prognostic accuracy.

  • 4

    The developed deep learning framework reclassifies NHG2 tumors into NHG1-like or NHG3-like subgroups, aiding in personalized treatment planning.

  • 5

    This approach aims to reduce overtreatment in low-risk NHG2 patients while ensuring high-risk patients receive appropriate intensified therapy.

Original Source(s)

A deep learning framework to stratify Nottingham histologic grade 2 breast tumors based on dynamic contrast-enhanced MRI

  • by Roham Hadidchi, Anchita Agrawal, Michael Z. Liu, Takouhie Maldijan, Yihui Zhu, Hien Quang Nguyen, Jinyu Lu, Della Makower, Susan Fineberg, Tim Q. Duong

  • December 17, 2025

Related Content

Latent class analysis of conventional ultrasound features: a novel approach to predicting non-response to neoadjuvant chemotherapy in breast cancer

Dana-Farber Research News 02.15.2026

This twice-monthly newsletter highlights recently published research where Dana-Farber faculty are listed as first or senior authors. The information is pulled from PubMed and this issue notes papers published from January 16 - 31.

  • by

  • February 15, 2026

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