IMAGE-RECONSTRUCTION BY A HOPFIELD NEURAL-NETWORK

The reconstruction of cross-sectional images from projections involves the solution of a large system of simultaneous equations in which the unknowns are attentuation coefficients associated with the cells cons tituting the image. As an alternative to iterative methods such as the algebraic reconstruction technique (ART), a modified linear form of t he Hopfield neural network with a summation layer to significantly dec rease the number of interconnections is proposed. Higher speed and imp roved SNR, compared to ART, have been obtained on the Shepp and Logan 'head phantom' divided into 100 X 100 cells.