Related Experiment Video
Updated: Apr 1, 2026
05:28
Clinical Imaging of Microwave Mammography
Published on: November 14, 2025
390
Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging
Chung-Ming Lo1, Yi-Chen Lai2, Yi-Hong Chou2
1Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan; Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.
Computer Methods and Programs in Biomedicine
|October 1, 2015
Summary
A new computer-aided diagnosis (CAD) system using shear-wave elastography (SWE) color data improves breast tumor malignancy assessment. Combining CAD with BI-RADS offers a promising diagnostic tool.
Area of Science:
- Medical Imaging
- Oncology
- Biophysics
Background:
- Breast tumor diagnosis relies on imaging techniques.
- Shear-wave elastography (SWE) provides quantitative elasticity information.
- Computer-aided diagnosis (CAD) systems can aid in interpreting medical images.
Purpose of the Study:
- To develop a CAD system using quantified color distributions in SWE for breast tumor malignancy evaluation.
- To assess the diagnostic performance of the CAD system.
Main Methods:
- 18 SWE features were extracted from 88 breast tumors (57 benign, 31 malignant).
- Features included color channel moments (mean, variance, skewness, kurtosis) and combined color vectors.
- SWE features were input into a logistic regression classifier for tumor classification.
Main Results:
- The CAD system achieved an 81% accuracy in classifying breast tumors.
- Integrating the CAD system with BI-RADS assessment significantly improved diagnostic performance (Az from 0.77 to 0.89, p<0.05).
Conclusions:
- The developed CAD system based on SWE features shows potential for breast tumor evaluation.
- Combining this CAD system with BI-RADS assessment offers a promising diagnostic suggestion for clinicians.
Keywords:
Breast cancerComputer-aided diagnosisHistogram momentShear-wave elastographyVector quantification
