Abstract: A machine-based learning system for predicting the presence of lesions indicative of axial spondyloarthritis in medical imaging data includes an image processor for receiving and processing one or more MRI image data set containing pelvic region and sacroiliac joint of a subject, and dividing said MRI image data set into a set of 3D voxels. The system also includes a voxel classifier for calculating for each of said the voxels one or more class probabilities of such voxel to contain a lesion of a particular type or being a non-lesion. The system also includes a lesion probability map generator for receiving the data produced by the voxel classifier and producing a probability intensity map for each of lesion types, in which one or more areas classified as lesion are highlighted; and an image display for displaying the output of the lesion probability map generator.

Abstract: A method of controlling a dynamic physical system comprising a plurality of variable quantities. A model of the system comprising a plurality of variables representing the variable quantities, and a plurality of respective rate equations that describe the rate of change of the variables, is obtained. A control term in at least one rate equation from the plurality of rate equations is identified. A rate control function is derived from, for at least one of the variables in the rate equation, the proportion of the variable to the growth rate of the rate equation, and the rate control function is applied to the control term to provide a stabilized control term. The dynamic physical system is then controlled by modifying at least one of the quantities represented by the variables in the control term, so that the control term derived from the modified quantities is substantially the same as the stabilized control term.