This letter introduces a novel approach to medical image segmentation using dendritic neurons and deep supervision. The proposed method, called Dendritic Deep Supervision Neural Network (DDNet), integrates dendritic neurons into the SegNet framework to enhance feature representation and improve segmentation accuracy. Dendritic neurons enable nonlinear feature mapping, capturing intricate details and fine-grained structures in medical images. Deep supervision, through multiple deep supervision signals, refines segmentation results at various scales, enhancing the model's ability to handle irregular sampling patterns and restore fine image details. The method is evaluated on several datasets, including DatasetB, STU, and Polyp, demonstrating superior performance compared to state-of-the-art methods. The contributions of the study include a novel network architecture, improved feature representation, enhanced training effectiveness, and superior performance. The experimental results, including ablation studies and parameter analysis, confirm the effectiveness of the proposed approach.This letter introduces a novel approach to medical image segmentation using dendritic neurons and deep supervision. The proposed method, called Dendritic Deep Supervision Neural Network (DDNet), integrates dendritic neurons into the SegNet framework to enhance feature representation and improve segmentation accuracy. Dendritic neurons enable nonlinear feature mapping, capturing intricate details and fine-grained structures in medical images. Deep supervision, through multiple deep supervision signals, refines segmentation results at various scales, enhancing the model's ability to handle irregular sampling patterns and restore fine image details. The method is evaluated on several datasets, including DatasetB, STU, and Polyp, demonstrating superior performance compared to state-of-the-art methods. The contributions of the study include a novel network architecture, improved feature representation, enhanced training effectiveness, and superior performance. The experimental results, including ablation studies and parameter analysis, confirm the effectiveness of the proposed approach.