Scholarlink

Background <p>Early prediction of pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer remains challenging. Traditional imaging lacks molecular sensitivity, while single-modality radiomics may miss tumor microenvironment dynamics. Integrating amide proton transfer-weighted imaging (APTWI)—quantifying protein levels linked to chemo-response—into multimodal radiomics may enable precise early pCR prediction, guiding personalized therapy. This study aims to develop and validate a multimodal radiomics model, integrating amide proton transfer-weighted imaging (APTWI), diffusion-weighted imaging (DWI), and early-phase contrast-enhanced T1WI, for preoperative prediction of pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC).</p> Methods <p>This retrospective study included 109 women (mean age 50 ± 10 years) with untreated breast cancer between May 2023 and August 2024, underwent NAC and pretreatment MRI scanning, including APTWI, DWI, and dynamic contrast-enhanced T1WI. Three-dimensional tumor segmentation was performed using ITK-SNAP. Radiomics features were extracted from APT, ADC maps, and enhanced subtraction images (30s/90s) using PyRadiomics, adhering to IBSI guidelines. LASSO regression selected predictive features, followed by Support Vector Machine and Logistic Regression classifiers with five-fold cross-validation. Performance was evaluated via ROC analysis, calibration curves, decision curve analysis (DCA), and SHAP interpretability.</p> Results <p>Patients were randomly divided into training (<i>n</i> = 77) and testing (<i>n</i> = 32) cohorts. The integrated model combining clinical (e.g. HER2, Ki-67) and radiomics features achieved superior predictive performance (AUC = 0.888, 95% CI: 0.768–1.000) versus single-modality radiomics (ADC: AUC = 0.708), standalone clinical (AUC = 0.815), or radiomics models (AUC = 0.763). Calibration showed strong prediction-reality agreement (Brier score = 0.157). DCA confirmed clinical utility at 10%–65% thresholds. SHAP identified HER2 status and ADC-derived texture features (e.g. Cluster Shade) as top predictors.</p> Conclusion <p>Multimodal integration of APTWI, DWI, contrast-enhanced T1WI, and clinicopathological biomarkers enables accurate preoperative pCR prediction in breast cancer, supporting personalized NAC management.</p> Advances in knowledge <p>Compared to single-modal imaging, our multimodal radiomics model provides more comprehensive biomarkers, thereby enabling personalized therapeutic decisions and optimizing NAC regimens to reduce overtreatment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multimodal radiomics for early prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer: integration of amide proton transfer weighted imaging in radiomics

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月7日

查看全文
  • Mingzhe Xu,
  • Ailing Wang,
  • Dongqiu Shan,
  • Xuejun Chen,
  • Renzhi Zhang,
  • Chunmiao Xu,
  • Junhui Yuan,
  • Jing Li,
  • Guangguang An,
  • Zhiwei Shen,
  • Yue Wu,
  • Funing Chu,
  • Guang Yang,
  • Jinrong Qu

摘要

Background

Early prediction of pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer remains challenging. Traditional imaging lacks molecular sensitivity, while single-modality radiomics may miss tumor microenvironment dynamics. Integrating amide proton transfer-weighted imaging (APTWI)—quantifying protein levels linked to chemo-response—into multimodal radiomics may enable precise early pCR prediction, guiding personalized therapy. This study aims to develop and validate a multimodal radiomics model, integrating amide proton transfer-weighted imaging (APTWI), diffusion-weighted imaging (DWI), and early-phase contrast-enhanced T1WI, for preoperative prediction of pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC).

Methods

This retrospective study included 109 women (mean age 50 ± 10 years) with untreated breast cancer between May 2023 and August 2024, underwent NAC and pretreatment MRI scanning, including APTWI, DWI, and dynamic contrast-enhanced T1WI. Three-dimensional tumor segmentation was performed using ITK-SNAP. Radiomics features were extracted from APT, ADC maps, and enhanced subtraction images (30s/90s) using PyRadiomics, adhering to IBSI guidelines. LASSO regression selected predictive features, followed by Support Vector Machine and Logistic Regression classifiers with five-fold cross-validation. Performance was evaluated via ROC analysis, calibration curves, decision curve analysis (DCA), and SHAP interpretability.

Results

Patients were randomly divided into training (n = 77) and testing (n = 32) cohorts. The integrated model combining clinical (e.g. HER2, Ki-67) and radiomics features achieved superior predictive performance (AUC = 0.888, 95% CI: 0.768–1.000) versus single-modality radiomics (ADC: AUC = 0.708), standalone clinical (AUC = 0.815), or radiomics models (AUC = 0.763). Calibration showed strong prediction-reality agreement (Brier score = 0.157). DCA confirmed clinical utility at 10%–65% thresholds. SHAP identified HER2 status and ADC-derived texture features (e.g. Cluster Shade) as top predictors.

Conclusion

Multimodal integration of APTWI, DWI, contrast-enhanced T1WI, and clinicopathological biomarkers enables accurate preoperative pCR prediction in breast cancer, supporting personalized NAC management.

Advances in knowledge

Compared to single-modal imaging, our multimodal radiomics model provides more comprehensive biomarkers, thereby enabling personalized therapeutic decisions and optimizing NAC regimens to reduce overtreatment.