Research on Medical Image Segmentation Algorithm Based on a Lightweight Attention Convolutional Neural Network

With the continuous development of medical imaging technology, medical image segmentation is playing an increasingly important role in clinical diagnosis and treatment planning. However, traditional deep learning methods, while ensuring segmentation accuracy, often suffer from issues such as large model size and high computational complexity. To address these challenges, this paper proposes a medical image segmentation algorithm based on a lightweight attention convolutional neural network. By incorporating lightweight convolution modules (such as depthwise separable convolutions and group convolutions), the proposed algorithm effectively reduces the number of model parameters and computational burden. At the same time, it integrates attention mechanisms — including channel attention and spatial attention — to enhance feature representation, thereby achieving higher accuracy and robustness across various medical image segmentation tasks. Experiments conducted on several public datasets, in comparison with mainstream methods, demonstrate significant advantages in both segmentation precision and operational efficiency. The research presented in this paper provides new ideas and references for the development of lightweight medical image segmentation techniques.