In this paper, we present a method for automatically segmenting the walls of retinal arteries in adaptive optics images. To our best knowledge, this is the first method adressing this problem in such images. To achieve this goal, we propose to model these walls as four curves approximately parallel to a common reference line located near to the center of vessels. Once this line detected, the curves are simultaneously positioned as near as possible to the borders of walls using an original tracking procedure to cope with deformations along vessels. Then, their positioning is refined using a deformable model embedding a parallelism constraint. Such an approach enables us to control the distance of the curves to their reference line and improve the robustness to image noise. This model was validated on healthy subjects by comparing the results against segmentations from physicians. Noticeably, the variability introduced by this model is smaller or very near to the inter-physicians variability.