High density trans-admittance mammography development and preliminary phantom tests

Evaluation of anomaly detection algorithm using trans-admittance mammography with 60 × 60 electrode array

Electrical impedance imaging has a potential to detect an early stage of breast cancer due to higher admittivity values compared with those of normal breast tissues. Specially, tumor size and extent of axillary lymph node involvement are important parameters to evaluate the breast cancer survival rate. We applied the anomaly detection algorithm to the high density trans-admittance mammography system for estimating the size and position of breast cancer. We tested 4 different size of anomaly with 3 different conductivity contrasts at 5 different depths. From a frequency difference trans-admittance map, we can readily observe the transversal position and estimate its size and depth. However, the size estimation was dependent on the admittivity contrast between anomaly and background. It requires the robust detection algorithm regardless of the conductivity contrast.

Combining extreme learning machines using support vector machines for breast tissue classification

In this paper, we present a new approach for breast tissue classification using the features derived from electrical impedance spectroscopy. This method is composed of a feature extraction method, feature selection phase and a classification step. The feature extraction phase derives the features from the electrical impedance spectra. The extracted features consist of the impedivity at zero frequency (I0), the phase angle at 500 KHz, the high-frequency slope of phase angle, the impedance distance between spectral ends, the area under spectrum, the normalised area, the maximum of the spectrum, the distance between impedivity at I0 and the real part of the maximum frequency point and the length of the spectral curve. The system uses the information theoretic criterion as a strategy for feature selection and the combining extreme learning machines (ELMs) for the classification phase. The results of several ELMs are combined using the support vector machines classifier, and the result of classification is reported as a measure of the performance of the system. The results indicate that the proposed system achieves high accuracy in classification of breast tissues using the electrical impedance spectroscopy.