Combining conventional ultrasound and ultrasound elastography to predict HER2 status in patients with breast cancer

Xiaoying Zhuo; Ji Lv; Binjie Chen; Jia Liu; Yujie Luo; Jie Liu; Xiaowei Xie; Jiao Lu; Ningjun Zhao

doi:10.3389/fphys.2023.1188502

Combining conventional ultrasound and ultrasound elastography to predict HER2 status in patients with breast cancer

Front Physiol. 2023 Jul 12:14:1188502. doi: 10.3389/fphys.2023.1188502. eCollection 2023.

Authors

Xiaoying Zhuo^{1

2}, Ji Lv^{3

4}, Binjie Chen³, Jia Liu⁵, Yujie Luo¹, Jie Liu¹, Xiaowei Xie¹, Jiao Lu¹, Ningjun Zhao^{3

6}

Affiliations

¹ Ultrasound Medicine Department of the Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
² Medical Imaging College of Xuzhou Medical University, Xuzhou, China.
³ Emergency Medicine Department of the Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
⁴ College of Computer Science and Technology, Jilin University, Changchun, China.
⁵ Pathology Department of the Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
⁶ Laboratory of Emergency Medicine, Second Clinical Medical College of Xuzhou Medical University, Xuzhou, China.

Abstract

Introduction: Identifying the HER2 status of breast cancer patients is important for treatment options. Previous studies have shown that ultrasound features are closely related to the subtype of breast cancer. Methods: In this study, we used features of conventional ultrasound and ultrasound elastography to predict HER2 status. Results and Discussion: The performance of model (AUROC) with features of conventional ultrasound and ultrasound elastography is higher than that of the model with features of conventional ultrasound (0.82 vs. 0.53). The SHAP method was used to explore the interpretability of the models. Compared with HER2- tumors, HER2+ tumors usually have greater elastic modulus parameters and microcalcifications. Therefore, we concluded that the features of conventional ultrasound combined with ultrasound elastography could improve the accuracy for predicting HER2 status.

Keywords: HER2; breast cancer; machine learning; shap; ultrasound.

Grants and funding

This research was funded by Xuzhou key research and development plan (social development) project—general medical and health project (KC22232; KC22236), Xuzhou National Clinical Key Specialty Cultivation Project (2018ZK004), The excellent young and middle-age talents project of the affiliated hospital of Xuzhou medical university (2019128009).