In this paper, a method to segment elongated objects is proposed. It is based on attribute profiles and area stability. Images are represented as component trees using a threshold decomposition. Then, some attributes are computed on each node of the tree. Finally, the attribute profile is analyzed to identify important events useful for segmentation tasks. In this work, a new attribute, combining geodesic elongation and area stability is defined. This methodol-ogy is successfully applied to the segmentation of cells in multiphoton fluores-cence microscopy images of engineered skin. Quantitative results are provided, demonstrating the performance and robustness of the new attribute. A compar-ison with MSER is also given.