Artificial neural networks as a method to improve the precision of subcutaneous adipose tissue thickness measurements by means of the optical device LIPOMETER

The LIPOMETER is an optical device for measuring the thickness of a subcuta neous adipose tissue layer. It illuminates the interesting layer, measures the backscattered light signals and from these, it computes absolute values of subcutaneous adipose tissue layer thickness (in mm). Previously, these light pattern values were fitted by nonlinear regression analysis to absolu te values provided by computed tomography. Nonlinear regression analysis mi ght provide slight limitations for our problem: a selected curve type canno t be changed afterwards during the application of the measurement device. A rtificial neural networks yield a more flexible approach to this fitting pr oblem and might be able to refine the fitting results. In the present paper we compare nonlinear regression analysis with the behaviour of different a rchitectures of multilayer feed forward neural networks trained by error ba ck propagation. Specifically, we are interested whether neural networks are able to yield a better fit of the LIPOMETER light patterns to absolute sub cutaneous adipose tissue layer thicknesses than the nonlinear regression te chniques. Different architectures of these networks are able to surpass the best result of regression analysis in training and test, providing higher correlation coefficients, regression lines with absolute values obtained fr om computed tomography closer to the line of identity, decreased sums of ab solute and squared deviations, and higher measurement agreement. (C) 2000 E lsevier Science Ltd. All rights reserved.