Related Experiment Video
Updated: Aug 11, 2026
Guidelines and Experience Using Imaging Biomarker Explorer (IBEX) for Radiomics
Published on: January 8, 2018
Predicting Breast Cancer with Super-Resolution Ultrasound-Based Radiomics: A Multicenter Retrospective Study
JiaLe Xu1, YuHang Zheng1, XiaoHong Jia1
1Department of Ultrasound, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, 200025 Shanghai, China (J.X., Y.Z., X.J., Q.H., S.X., Y.D., J.Z.); College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China (J.X., Y.Z., X.J., Q.H., S.X., Y.D., J.Z.).
A new radiomics framework combining ultrasound (US) and super-resolution ultrasound (SRUS) with clinical data accurately distinguishes benign from malignant breast lesions. This automated approach enhances microvasculomics for improved breast cancer diagnosis.
Area of Science:
- Medical Imaging
- Oncology
- Ultrasound Technology
Background:
- Super-resolution ultrasound (SRUS) for breast lesion characterization is hindered by manual analysis.
- Microvasculomics offers automated quantitative microvascular analysis, a potential solution.
Purpose of the Study:
- To develop and validate a radiomic framework integrating B-mode ultrasound (US), SRUS, and clinical data.
- To differentiate benign from malignant breast lesions using this multimodal approach.
Main Methods:
- Retrospective, multicenter study of 742 female patients.
- Extraction of radiomic features from B-mode and SRUS images.
- Construction of support vector machine models using single-modality and multimodal data.
Main Results:
- The integrated clinical-radiomic model achieved high AUCs (0.921 internal, 0.872 external).
- In the BI-RADS 4A subgroup, the model showed an AUC of 0.876 and 97.5% negative predictive value.
Conclusions:
- The developed radiomics framework demonstrates robust breast cancer prediction.
- This pipeline offers a reference for SRUS-based microvasculomic analysis.
