MRI-Based Model Accurately Predicts Early Treatment Response in Triple-Negative Breast Cancer

A new study published in the American Journal of Roentgenology (AJR) presents a clinically useful MRI-based model for predicting early pathologic complete response (pCR) in patients undergoing neoadjuvant chemoimmunotherapy (NACI) for triple-negative breast cancer (TNBC). The predictive model offers a practical approach to guide treatment decisions early in the therapy process, allowing clinicians to tailor regimens based on patient response.

“This MRI-based predictive model could facilitate timely tailoring of clinical regimens after immunotherapy initiation by informing optimal de-escalation strategies for responders while prompting therapeutic adaptations for nonresponders,” said senior and corresponding author Dr. Changhong Liang of the radiology department at Guangdong Provincial People’s Hospital and the Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application at Southern Medical University in Guangzhou, China.

The study analyzed MRI data from two distinct patient groups: a training cohort of 90 women (average age 49) treated between January 2018 and September 2024, and an external validation cohort of 29 women (average age 46) from publicly available clinical trial datasets. All participants were diagnosed with TNBC and underwent breast MRI scans, including dynamic contrast-enhanced imaging, both before treatment and after the first cycle of NACI.

Two radiologists assessed key MRI features, focusing particularly on the percentage enhancement (PE) reduction, a semi-quantitative metric reflecting the reduction in intralesional enhancement—essentially indicating early treatment effects on tumor vascularity and structure. Using multivariable logistic regression, the researchers built a predictive model incorporating independent predictors of pCR following the full course of NACI.

The final model combined three critical imaging markers:

• Tumor unifocality observed on pretreatment MRI,

• Early tumor shrinkage of 37% or more after the first NACI cycle,

• Significant percentage enhancement reduction on early post-treatment MRI.

When evaluated on the external test cohort, the model demonstrated strong performance, with an area under the curve (AUC) of 0.88, sensitivity of 74%, and specificity of 90%—indicating its potential as a reliable early predictor of therapeutic response.

This work underscores the value of integrating imaging biomarkers into oncologic treatment planning, particularly in aggressive cancers like TNBC, where early identification of responders and nonresponders can critically impact outcomes. By enabling informed adjustments to treatment strategies after just one cycle of therapy, the model may support more personalized, effective care and reduce unnecessary treatment burdens for patients unlikely to benefit from prolonged immunochemotherapy.

With further validation, this model could become a key component in the decision-making process for TNBC treatment, helping to accelerate the shift toward precision oncology.