Related Experiment Video
Updated: Jan 18, 2026
08:36
Ultrasound Imaging-guided Intracardiac Injection to Develop a Mouse Model of Breast Cancer Brain Metastases Followed by Longitudinal MRI
Published on: March 6, 2014
19.6K
Ultrasound Video-Based Radiomics Analysis for Differentiating Benign and Malignant Breast Lesions.
Jiangfeng Wu1, Lijing Ge1, Yun Jin1
1Department of Ultrasound, Dongyang People's Hospital, Dongyang, China.
Technology in Cancer Research & Treatment
|September 8, 2025
Summary
Combining ultrasound radiomics and clinical data significantly improves breast tumor diagnosis. This integrated approach enhances accuracy in distinguishing benign from malignant lesions, aiding clinical decisions.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Oncology
Background:
- Accurate differentiation of benign and malignant breast lesions is crucial for effective patient management.
- Conventional methods like Breast Imaging Reporting and Data System (BI-RADS) classification have limitations in diagnostic performance.
Purpose of the Study:
- To evaluate a combined model using ultrasound video-based radiomics and clinical variables for improved breast lesion diagnosis.
- To compare the diagnostic performance of the combined model against clinical and radiomics-only models, and BI-RADS classification.
Main Methods:
- Retrospective analysis of 346 breast ultrasound videos (173 benign, 173 malignant).
- Extraction and selection of radiomics features from segmented tumor regions using 3D Slicer.
- Construction and performance evaluation (AUC) of clinical, radiomics, and combined models using ROC analysis.
Main Results:
- The combined model achieved a superior AUC of 0.926, outperforming the clinical model (0.873), radiomics model (0.836), and BI-RADS (0.737).
- Internal validation confirmed the combined model's robustness with AUCs ranging from 0.901 to 0.954.
Conclusions:
- The integration of ultrasound video-based radiomics with clinical data significantly enhances the differentiation of benign and malignant breast tumors.
- This advanced diagnostic approach offers potential for improved accuracy and more precise clinical decision-making in breast oncology.
