Head and neck tumors are prevalent malignant tumors in China, with prognosis significantly influenced by cervical lymph node metastasis. In medical practice, magnetic resonance imaging (MRI) is employed to identify metastatic lymph nodes. However, MRI images often suffer from blurred edges and low contrast between the lesion and surrounding tissue. This paper introduces a segmentation network tailored for metastatic lymph nodes in head and neck tumors. Initially, a cross-layer and cross-field attention module is developed, integrating features from both deep and shallow layers to enhance the shape representation of metastatic lymph nodes through a self-attention mechanism. This module improves contextual semantic understanding across different receptive fields, allowing for pixel-level fusion of shallow and deep feature maps, thereby enhancing the morphological details of metastatic lymphatic nodes. Subsequently, a multi-scale feature fusion module is designed to amalgamate features across various scales in the feature pyramid, enriching the morphological details of the lymph nodes. Furthermore, an enhanced attention prediction head module is implemented, combining parallel self-attention and gate channel transformation to accentuate the lesion area and refine its boundaries on the feature map. The network's effectiveness is confirmed using a clinical dataset of lymph node metastasis medical images. The performance metrics, APdet, APseg, ARdet, ARseg, mAPdet, and mAPseg for lymph node metastasis lesion segmentation are 74.88%, 74.12%, 63.11%, 62.28%, 74.64%, and 74.04%, respectively. This network provides precise detection and segmentation of lymph node metastasis lesions, offering significant benefits for lymph node diagnosis.