Accurate segmentation of lymph nodes in head and neck (H&N) CT images is essential for the radiotherapy planning of the H&N cancer. Atlas-based segmentation methods are widely used for the automated segmentation of such structures. Multi-atlas approaches are proven to be more accurate and robust than using a single atlas. We have recently proposed a general Markov random field (MRF)-based framework that can perform edge-preserving smoothing of the labels at the time of fusing the labels itself. There are three main contributions of this paper: First, we reformulate the "shape based averaging" (SBA) fusion method to fit into the general MRF-based fusion framework. Second, we evaluate the following fusion algorithms for the segmentation of H&N lymph nodes: (i) STAPLE, (ii) SBA, (iii) SBA+MRF, (iv) majority voting (MV), (v) MV+MRF, (vi) global weighted voting (GWV), (vii) GWV+MRF, (viii) local weighted voting (LWV) and (ix) LWV+MRF. Finally, we also study the effect varying the number of atlases on the performance of the above algorithms.