Research on Medical Image Segmentation Algorithm Based on a Lightweight Attention Convolutional Neural Network
DOI:
https://doi.org/10.71222/0z430t65Keywords:
medical image segmentation, lightweight network, attention mechanism, Convolutional Neural Network, deep learningAbstract
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.
References
1. X. Li, Y. Jiang, M. Li, and S. Yin, “Lightweight attention convolutional neural network for retinal vessel image segmentation,” IEEE Trans. Ind. Inform., vol. 17, no. 3, pp. 1958–1967, Mar. 2020, doi; 10.1109/TII.2020.2993842.
2. J. Chen, W. Chen, A. Zeb, and D. Zhang, “Segmentation of medical images using an attention embedded lightweight net-work,” Eng. Appl. Artif. Intell., vol. 116, p. 105416, Feb. 2022, doi: 10.1016/j.engappai.2022.105416.
3. V. K. Singh, et al., “Prior wavelet knowledge for multi-modal medical image segmentation using a lightweight neural net-work with attention guided features,” Expert Syst. Appl., vol. 209, p. 118166, May 2022, doi: 10.1016/j.eswa.2022.118166.
4. Q. Zhou, Q. Wang, Y. Bao, L. Kong, X. Jin, and W. Ou, “LAEDNet: A lightweight attention encoder–decoder network for ul-trasound medical image segmentation,” Comput. Electr. Eng., vol. 99, p. 107777, Jul. 2022, doi: 10.1016/j.compeleceng.2022.107777.
5. Q. Zhou, Z. Huang, M. Ding, and X. Zhang, “Medical image classification using lightweight CNN with spiking cortical mod-el-based attention module,” IEEE J. Biomed. Health Inform., vol. 27, no. 4, pp. 1991–2002, Apr. 2023, doi: 10.1109/JBHI.2023.3241439.
6. H. Liu, G. Huo, Q. Li, X. Guan and M. L. Tseng, “Multiscale lightweight 3D segmentation algorithm with attention mecha-nism: Brain tumor image segmentation,” Expert Syst. Appl., vol. 214, p. 119166, Sep. 2023, doi: 10.1016/j.eswa.2022.119166.
7. S. Iqbal, T. M. Khan, S. S. Naqvi, A. Naveed, M. Usman, H. A. Khan, and I. Razzak., “LDMRes-Net: A lightweight neural net-work for efficient medical image segmentation on IoT and edge devices,” IEEE J. Biomed. Health Inform., vol. 28, no. 7, pp. 3860–3871, Jul. 2023, doi: 10.1109/JBHI.2023.3331278.
8. Z. Han, M. Jian, and G.-G. Wang, “ConvUNeXt: An efficient convolution neural network for medical image segmentation,” Knowl.-Based Syst., vol. 253, p. 109512, Oct. 2022, doi: 10.1016/j.knosys.2022.109512.
9. T. Agrawal and P. Choudhary, “ALCNN: Attention-based lightweight convolutional neural network for pneumothorax de-tection in chest X-rays,” Biomed. Signal Process. Control, vol. 79, p. 104126, Jan. 2023, doi:10.1016/J.BSPC.2022.104126.
10. X. Lin, L. Yu, K. T. Cheng, and Z. Yan, “BATFormer: Towards boundary-aware lightweight transformer for efficient medical image segmentation,” IEEE J. Biomed. Health Inform., vol. 27, no. 7, pp. 3501–3512, Jul. 2023, doi: 10.1109/JBHI.2023.3266977.
