PubMed Health⌕ Search

Biomedical subjects

Daryl G Beetner

Publications and source records attributed to Daryl G Beetner.

3 recordsLinked to original sources

Detection of basal cell carcinoma using electrical impedance and neural networks.

Variations in electrical impedance over frequency might be used to distinguish basal cell carcinoma (BCC) from benign skin lesions, although the patterns that separate the two are nonobvious. Artificial neural networks (ANNs) may be good pattern classifiers for this application. A preliminary study to show the potential of neural networks to distinguish benign from malignant skin lesions using electrical impedance is presented. Electrical impedance was measured in vivo from 1 kHz to 1 MHz at five virtual depths on 18 BCC and 16 benign or premalignant lesions. A feed-forward neural network was trained using back propagation to classify these lesions. Two methods of preprocessing were used to account for the impedance of normal skin and the size of the lesion, one based on estimating the impedance of the lesion relative to adjacent normal skin and one based on estimating the impedance of the lesion independent of size or surrounding normal skin. Neural networks were able to classify measurements in a test set with 100% accuracy for the first preprocessing technique and 85% accuracy for the second. These results indicate electrical impedance may be a promising clinical diagnostic tool for basal cell carcinoma or other forms of skin cancer.

Algorithms↗

Estimation of heart-surface potentials using regularized multipole sources.

Direct inference of heart-surface potentials from body-surface potentials has been the goal of most recent work on electrocardiographic inverse solutions. We developed and tested indirect methods for inferring heart-surface potentials based on estimation of regularized multipole sources. Regularization was done using Tikhonov, constrained-least-squares, and multipole-truncation techniques. These multipole-equivalent methods (MEMs) were compared to the conventional mixed boundary-value method (BVM) in a realistic torso model with up to 20% noise added to body-surface potentials and +/-1 cm error in heart position and size. Optimal regularization was used for all inverse solutions. The relative error of inferred heart-surface potentials of the MEM was significantly less (p < 0.05) than that of the BVM using zeroth-order Tikhonov regularization in 10 of the 12 cases tested. These improvements occurred with a fourth-degree (24 coefficients) or smaller multipole moment. From these multipole coefficients, heart-surface potentials can be found at an unlimited number of heart-surface locations. Our indirect methods for estimating heart-surface potentials based on multipole inference appear to offer significant improvement over the conventional direct approach.

Adult↗

Differentiation among basal cell carcinoma, benign lesions, and normal skin using electric impedance.

This paper presents a preliminary study showing the diagnostic potential of electrical impedance to detect basal cell carcinoma (BCC). Electrical impedance was measured in vivo from 1 kHz to 1 MHz on 24 human subjects over BCC (19 lesions), over benign tumors (11 lesions), and over normal skin (all 24 patients). Lesions ranged from 2-15 mm in diameter. Indexes based on the magnitude (MIX), phase (PIX), real-part (RIX) and imaginary-part (IMIX) of impedance were calculated for each measurement. Significant differences were found between measurements over BCC, benign lesions and normal skin for indexes MIX, PIX, and IMIX (P = 0.04 to P = 7 x 10(-7)). Indexes were generally smaller for measurements of BCC than for benign lesions or normal skin. Differences were not a result of differences in the patient's age or the measurement location. The large size of our measurement electrode (10 mm) probably limited our ability to differentiate lesions because significant amounts of normal skin were included in each lesion measurement. A linear regression fit of data with tumor size suggests that a smaller probe or more sophisticated analysis techniques may improve differentiation. Results suggest that electrical impedance could be used to provide rapid and noninvasive differentiation of BCC from similar looking benign lesions.

Adult↗