Abstract: In recent years, cardiac medical image segmentation using the variational level-set method has been widely applied in image processing. However, the uneven grayscale of images and the symbolic distance function in the gradient descent method lead to issues such as computational complexity and high computational cost during segmentation. To address these challenges, this paper introduces modifications to the edge detection function based on the adaptive local fitting model and develops an improved active contour model. This model is combined with fast computational image segmentation algorithm, alternating direction method of multipliers (ADMM), to solve the level-set equations. The proposed approach, called the neighbor level set minimized with the ADMM method, incorporates a data fitting term that leverages neighbor region information for enhanced medical image segmentation. The introduction of the edge detection function smooths homogeneous regions and enhances edge information. The proposed model effectively addresses common issues in medical image segmentation, such as intensity inhomogeneity, and produces accurate and fast results. The problem of inaccurate segmentation is resolved by introducing a new level set active contour model that incorporates neighborhood information to precisely segment the region of interest. The model mitigates the impact of grayscale variations by leveraging local contextual information, which improves segmentation accuracy. The main purpose of this paper is to propose a new model for medical image segmentation based on a neighborhood-level set framework and the ADMM method. Our energy function comprises three terms: the data fitting term, the length term, and the regularization term, which together balance the fitting energy and ensure a smooth boundary. The ADMM method is then employed to minimize the energy function and achieve the final segmentation result. Traditional segmentation methods, such as gradient descent, are often time-consuming, computationally complex, and costly. In contrast, the proposed approach breaks down a complex problem into several simpler sub-problems that can be solved sequentially to enable faster and more accurate resolution using the ADMM algorithm. This approach also effectively addresses the challenges posed by level-set equations. Experimental results demonstrate that the new model is not only robust to uneven grayscale images but also achieves higher segmentation efficiency and accuracy. The model demonstrates the ability to quickly generate curves and accurately represent the contours of cardiac images. To evaluate its effectiveness, we conduct comparative experiments using the Dice coefficient and Jaccard index as evaluation metrics. The experimental results show that our proposed model consistently achieves higher Dice coefficients and Jaccard indices compared with other existing models. This achievement highlights its superior segmentation performance. In conclusion, our improved level-set contour model, combined with the fast computational ADMM algorithm, provides an effective solution to the challenges commonly encountered in medical image segmentation. It offers significant improvements in accuracy, computational efficiency, and cost-effectiveness.