Researchers recently developed a multimodal radiomics model to enhance early multimodal radiomics pCR prediction for patients undergoing neoadjuvant chemotherapy (NAC). Accurate prediction of pathological complete response (pCR) remains a critical goal in breast cancer management. However, traditional imaging techniques often lack the molecular sensitivity required for precise assessment. This study addresses this gap by integrating Amide Proton Transfer-weighted imaging (APTWI) with Diffusion-Weighted Imaging (DWI) and contrast-enhanced T1WI.

Improving Clinical Outcomes with Multimodal Radiomics pCR Prediction

The study involved 109 women who underwent pretreatment MRI scanning. These advanced scans included APTWI, which quantifies protein levels directly linked to chemotherapy response. Furthermore, the team performed three-dimensional tumor segmentation to extract high-dimensional features. Specifically, they utilized LASSO regression and Support Vector Machine classifiers to select the most predictive features. Consequently, the resulting integrated model demonstrated superior accuracy compared to conventional single-modality methods.

The results showed that the integrated model achieved an Area Under the Curve (AUC) of 0.888. This performance significantly surpassed standalone clinical models and single-sequence radiomics. Moreover, SHAP interpretability analysis highlighted HER2 status and specific ADC-derived texture features as top predictors. Therefore, this multimodal approach provides a comprehensive set of biomarkers. These findings support personalized therapeutic decisions and help clinicians optimize chemotherapy regimens while minimizing the risk of overtreatment.

Frequently Asked Questions

What is Amide Proton Transfer-weighted imaging (APTWI)?

APTWI is a molecular MRI technique that quantifies mobile protein and peptide levels. Since high protein levels often correlate with tumor proliferation and response to therapy, APTWI provides unique metabolic insights that standard imaging lacks.

How does multimodal radiomics benefit breast cancer patients?

By combining various imaging sequences and clinical markers, multimodal radiomics offers a more precise prediction of how a tumor will respond to chemotherapy. This allows doctors to tailor treatments specifically to the patient, potentially avoiding ineffective therapies and reducing side effects.

Disclaimer: This content is for informational and educational purposes only and does not constitute medical advice, diagnosis, or treatment. Always seek the advice of a qualified healthcare provider with any questions regarding a medical condition. Refer to the latest local and national guidelines for clinical practice.

References

Xu M et al. Multimodal radiomics for early prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer: integration of amide proton transfer weighted imaging in radiomics. BMC Med Imaging. 2026 Apr 07. doi: 10.1186/s12880-026-02311-5. PMID: 41947063.

Zaccagna F, et al. Radiomics and machine learning in breast cancer. Br J Radiol. 2019;92(1103):20180464. doi: 10.1259/bjr.20180464.

Lambin P, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14(12):749-762. doi: 10.1038/nrclinonc.2017.141.