Early detection of breast cancer significantly increases the chance of recovery. Conventional screening methods including x-ray mammography have several drawbacks such as ionizing radiation, uncomfortable breast compression, and a relatively high miss rate. Our research team is developing a microwave-based breast cancer detection system as a low-cost screening tool that can complement existing technologies. The system uses an antenna array to propagate low-power microwave signals into the breast and records the scattered waveforms in order to detect malignancies. We develop various machine learning techniques to process the recorded signals and to decide whether they correspond to a healthy breast.
Our research direction on statistical signal processing aspects of microwave breast cancer detection include:
We have also finished the first round of clinical trials, please click here to see more project details.
We developed three classification architecture to fuse information from all signals recorded by a multistatic antenna array
Feature Fusion Architecture Classifier Fusion Architecture Ensemble Selection Architecture
System and data
Performance comparison with delay-multiply-and-sum (DMAS)-based and generalized likelihood ratio test (GLRT)-based algorithm:
Breast phantom data Clinical trial data
"Microwave Breast Cancer Detection via Cost-sensitive Ensemble Classifiers: Phantom and Patient Investigation",Biomedical Signal Processing and Control, vol. 31, 01/2017.
2. "Comparison of microwave breast cancer detection results with breast phantom data and clinical trial data: varying the number of antennas", European Conf. Antennas and Propag. (EuCAP), Davos, Switzerland, 04/2016.
"Cost-sensitive ensemble classifiers for microwave breast cancer detection", IEEE Int. Conf. Acoustics Speech and Sig. Proc. (ICASSP), Brisbane, Australia, 04/2015.
"Imaging-based Classification Algorithms on Clinical Trial Data with Injected Tumour Responses", European Conf. Antennas and Propag. (EuCAP), Lisbon, Portugal, 04/2015.
"Investigation of classification algorithms for a prototype microwave breast cancer monitor", European Conf. Antennas and Propag. (EuCAP), The Hague, The Netherlands, Apr. 2014.