Related Experiment Video
Updated: Jul 4, 2026
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Machine Learning Classification of Breast Density from Bioimpedance Signals
Christopher Thompson1, Marc Goldfinger1, Jacobo Fernandez-Vargas1
1Zedsen Limited.
Studies in Health Technology and Informatics
|July 3, 2026
Summary
Machine learning can classify breast density using Time-Domain Bioimpedance Sensing (TD-BIS) signals. This pilot study shows TD-BIS is a feasible alternative to mammography for assessing breast cancer risk factors.
Area of Science:
- Biomedical Engineering
- Radiology
- Machine Learning
Background:
- Breast density is a significant risk factor for breast cancer.
- Mammography is the standard for breast density assessment but has limitations.
- Alternative methods are needed to improve breast cancer risk evaluation.
Purpose of the Study:
- To evaluate the feasibility of using machine learning with Time-Domain Bioimpedance Sensing (TD-BIS) for breast density classification.
- To explore TD-BIS as a potential alternative to mammography for breast cancer risk assessment.
Main Methods:
- A pilot study was conducted to collect Time-Domain Bioimpedance Sensing (TD-BIS) signals.
- Machine learning algorithms were applied to classify breast density based on TD-BIS data.
Main Results:
- The study demonstrated the feasibility of classifying breast density using TD-BIS signals.
- Machine learning models showed potential in differentiating breast densities from bioimpedance data.
Conclusions:
- Time-Domain Bioimpedance Sensing (TD-BIS) shows promise as a novel method for breast density assessment.
- This approach could offer a viable alternative to traditional mammography in identifying breast cancer risk factors.