<p>Tooth segmentation in dental panoramic X-ray images is a task of great clinical importance. However, previous studies have often neglected the importance of edge information, resulting in inaccurate tooth segmentation with blurred borders and low contrast. In this paper, we propose EASAM, an edge-aware fusion transformer method designed to utilize edge information in order to assist salient features for dental panoramic X-ray image segmentation. A dual-stream structure is used, where the image coding layer of SAM is used for salient branching, and the other part uses a U-Net-like CNN structure for edge branching. Then the salient branch is fused with the edge branch, and the fused edge feature map is fused with the salient branch result to feed into the later structure. Extensive experiments on three public benchmark datasets demonstrate the effectiveness and superiority of our proposed method compared to other state-of-the-art methods. The method demonstrates the ability to accurately identify and analyze tooth structure, thus providing important information for dental diagnosis, treatment planning, and research.</p>