Related Experiment Video
Updated: Aug 18, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Predicting the Early Response to Neoadjuvant Therapy with Breast MR Morphological, Functional and Relaxometry
Roxana Pintican1,2, Radu Fechete3, Bianca Boca1
1Department of Radiology, "Iuliu Hatieganu" University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania.
MR relaxometry shows promise in predicting early breast cancer treatment response. T2 min values and nodal status combined offer a powerful tool for assessing neoadjuvant therapy effectiveness.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Early prediction of treatment response in breast cancer is crucial for optimizing neoadjuvant therapy (NAT).
- Current methods for assessing early response have limitations.
- MR relaxometry offers a novel approach to quantitatively evaluate tissue properties.
Purpose of the Study:
- To evaluate the role of MR relaxometry and proton density analysis in predicting early treatment response to NAT in breast cancer patients.
- To determine if specific relaxometry parameters can identify responders versus non-responders after two cycles of NAT.
Main Methods:
- Prospective study of 59 breast cancer patients undergoing MRI before (MRI1) and after two NAT cycles (MRI2).
- MR relaxometry maps and seven derived parameters were obtained from MRI1.
- Histopathology, T2 features, and ADC values were also analyzed.
- Response was defined by size changes on MRI2.
Main Results:
- 50 patients (79.3%) responded to NAT, while 13 (20.7%) did not.
- Nodal status (N0 vs. N2) was associated with response (p=0.005).
- T2 min relaxometry value showed association with response (p=0.017), with an AUC of 0.715.
- A combined model of T2 min and N stage achieved a higher AUC of 0.826 (p<0.001).
Conclusions:
- MR relaxometry, particularly T2 min values, shows potential as a tool for predicting early treatment response in breast cancer patients undergoing NAT.
- Combining T2 min relaxometry with nodal status significantly improves prediction accuracy.
- This quantitative imaging approach may aid in tailoring breast cancer treatment strategies.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020