Background Preoperative distinguish between luminal and non-luminal cancers is crucial for treatment decisions making in patients with breast cancers, as neoadjuvant treatment is recommended for non-luminal tumors instead of luminal tumors. Nevertheless, existing methods have several limitations and there is no effective non-invasive approach to predict molecular subtypes of breast cancer. Purpose To construct and validate an radiomics model based on ultrasound and dynamic contrast enhanced magnetic resonance imaging (DCE MRI) for preoperative non-invasive prediction of breast cancer molecular subtypes. Methods A total of 655 breast cancer patients from two centers were retrospectively collected, with 551 patients from center 1 allocated in a 3:1 ratio into a training set (n = 413) and an internal testing set (n = 138), and 104 cases from center 2 serving as an independent external validation set. Eight machine learning algorithms were employed to construct ultrasound radiomics model (RUS), MRI radiomics model (RMRI), and combined model (RMRI+US) based on both ultrasound and MR images. The models were tested on the internal testing set, and the algorithm with the best predictive performance was selected for further model performance validation on the external validation set. Results The RMRI+US constructed by support vector machine showed the best predictive performance, with AUC of 0.973 (95%CI: 0.958, 0.988) and 0.872 (95%CI: 0.805, 0.939) in the training and internal testing sets, respectively, significantly higher than those of the RUS and RMRI (all P < 0.05). The AUC of the RMRI+US was 0.835 (95%CI: 0.750, 0.921) in the external validation set outperformed single-modality radiomics models (RUS, 0.684 [95%CI: 0.560, 0.808], P = 0.066; RMRI, 0.740 [95%CI: 0.620, 0.860], P = 0.113), although there was no significant statistical difference. Conclusion The radiomics combined model based on pretherapeutic ultrasound and DCE MRI demonstrates potential value for differentiating luminal and non-luminal breast cancers, and may serve as a complementary tool to support clinical decision-making.

The radiomics models based on ultrasound and DCE MRI for predicting molecular subtypes of breast cancer

期刊论文
出版模式：

开放获取
发表日期：

2026年4月14日

查看全文

Rushuang Mao,
Hongxin Zheng,
Xiaofeng Tang,
Liang Yang,
Yafang Zhang,
Jianhua Zhou

摘要

Background

Preoperative distinguish between luminal and non-luminal cancers is crucial for treatment decisions making in patients with breast cancers, as neoadjuvant treatment is recommended for non-luminal tumors instead of luminal tumors. Nevertheless, existing methods have several limitations and there is no effective non-invasive approach to predict molecular subtypes of breast cancer.

Purpose

To construct and validate an radiomics model based on ultrasound and dynamic contrast enhanced magnetic resonance imaging (DCE MRI) for preoperative non-invasive prediction of breast cancer molecular subtypes.

Methods

A total of 655 breast cancer patients from two centers were retrospectively collected, with 551 patients from center 1 allocated in a 3:1 ratio into a training set (n = 413) and an internal testing set (n = 138), and 104 cases from center 2 serving as an independent external validation set. Eight machine learning algorithms were employed to construct ultrasound radiomics model (R_US), MRI radiomics model (R_MRI), and combined model (R_MRI+US) based on both ultrasound and MR images. The models were tested on the internal testing set, and the algorithm with the best predictive performance was selected for further model performance validation on the external validation set.

Results

The R_MRI+US constructed by support vector machine showed the best predictive performance, with AUC of 0.973 (95%CI: 0.958, 0.988) and 0.872 (95%CI: 0.805, 0.939) in the training and internal testing sets, respectively, significantly higher than those of the R_US and R_MRI (all P < 0.05). The AUC of the R_MRI+US was 0.835 (95%CI: 0.750, 0.921) in the external validation set outperformed single-modality radiomics models (R_US, 0.684 [95%CI: 0.560, 0.808], P = 0.066; R_MRI, 0.740 [95%CI: 0.620, 0.860], P = 0.113), although there was no significant statistical difference.

Conclusion

The radiomics combined model based on pretherapeutic ultrasound and DCE MRI demonstrates potential value for differentiating luminal and non-luminal breast cancers, and may serve as a complementary tool to support clinical decision-making.