An introduction to electrical capacitance tomography and a brief background of multi-modal tomography is given. The motivation for a neurocomputing solution to the inverse problem of image reconstruction is discussed together with a brief overview of previous work in this field. The techniques developed form the basis for training a single artificial neural network to perform three-component flow imaging using simulated data. A;dedicated thresholding function is demonstrated to accommodate three distinct and stable regions for gas, oil and water component estimation. Preliminary results indicate the feasibility of this neural solution for three-component imaging. Noise performance of the three-component reconstructor is also analysed, and the image reconstruction for test patterns and noise performance of this network are illustrated.