Radiotherapy planning requires accurate delin-eations of the critical structures. Atlas-based segmentation has been shown to be very efficient to delineate brain structures. On other parts of the body, using an atlas built from one single image as for the brain does not seem adequate, since the structures to be delineated are not clearly defined. Using only one image may then introduce undesirable bias. Building an atlas from a set of segmented images address this issue, but it will then depend on the choice of the registration method used to fuse the images. This point is generally not addressed in the literature, and is the aim of this article. Since the atlas is designed to delineate structures, we will evaluate together both the registration method used to build the atlas, and the one used to deform the built atlas on an individual image. We illustrate our framework on the construction of an atlas of the head and neck area. Using atlas-based segmentation to delineate critical structures in this area seems indeed very interesting, as a large part of the cancers (7 %) arise there. We compare the results obtained using three different methods on a real dataset of manually segmented images.