Wideband microwave imaging systems are recently used in various applications including airport security, surveillance, through-wall imaging and medicine. For the operation of such high-resolution systems, sparse multiple-input-multiple output (MIMO) arrays are of interest to reduce the hardware complexity and cost of conventional planar arrays. In this paper, we present a method for the optimal design of two-dimensional MIMO arrays in near-field imaging. Using a statistical framework, the optimality criterion is defined based on the image reconstruction quality. A modified version of the sequential backward selection algorithm is used to optimize the criterion over all possible locations of desired number of antenna elements. The designs obtained with the algorithm are compared with the commonly used sparse array configurations such as Mills Cross array and curvilinear structure composed array in terms of image reconstruction quality.