We present a framework for identifying disease states by classifying cells in the pathological regions of tissues into different categories. We use conditional random fields (CRF) to incorporate characteristics of cells and their spatial distributions. The efficacy of CRF to model cell-cell feature interactions is demonstrated by using a lung tissue dataset and a synthesized cancer tissue dataset. Comparisons with an independent cell model and a contextual model based on a Markov random field indicate that CRF effectively incorporates features of both cells and their spatial distributions for identification of pathological cells.