Author(s)

MengYuan Cao^1*, WenXuan Hong¹, XinRui Li², JiaLu Zhao¹

Affiliation(s)

¹School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 10048, China.

²School of Humanities and Social Sciences, Beihang University, Beijing 100191, China.

Corresponding Author

MengYuan Cao

ABSTRACT

In order to solve the problems of blurred lesion boundaries, missed small targets and sensitivity to background interference in 2D medical image segmentation of traditional U-Net, an improved model CB-V-UNET is proposed that fuses channel and spatial attention mechanism. Firstly, the model embeds the Convolutional Block Attention Module (CBAM) in the jump connection path of the standard U-Net to enhance the response of key areas and suppress irrelevant background noise through adaptive weighted channel features and spatial position information. Secondly, relying on the attention enhancement structure of the model, the weak boundary feature capture ability and small target recognition accuracy are optimized to make up for the structural defects of the original U-Net. Finally, model training and validation experiments were carried out on the ISIC 2018 skin lesion segmentation dataset and the DRIVE retinal vascular segmentation dataset, and the results showed that the Dice coefficient of CB-V-UNET on the ISIC 2018 dataset was 85.63%, the average intersection and union ratio (mIoU) was 85.41%, and the Dice coefficient on the DRIVE dataset was 82.15%, which was better than the original U-Net and various mainstream variants. The ablation experiment further confirmed the effectiveness of the CBAM module. This scheme provides an effective solution to improve the segmentation accuracy of small targets and weak boundary structures in medical images, and has important clinical application value.

KEYWORDS

Medical image segmentation; U-Net; CBAM attention mechanism; Skin lesions; Retinal vascularization

CITE THIS PAPER

MengYuan Cao, WenXuan Hong, XinRui Li, JiaLu Zhao. U-Net medical image segmentation study based on CBAM attention mechanism. World Journal of Information Technology. 2026, 4(1): 41-47. DOI: https://doi.org/10.61784/wjit3081.

REFERENCES

[1] Luo C, Zhang Y, Li W. An Improved U-Net with Image Enhancement for Underwater Bridge Crack Segmentation. Journal of Computational Design and Engineering, 2022, 9(3): 892-905.

[2] Tan Y, Chen W, Luo X. Fusion of U-Net and Mask R-CNN for Exterior Wall Crack Segmentation with High Geometric Fitting Quality. IEEE Access, 2023, 11: 45678-45691.

[3] Yao J, Wang Z, Gao Y. Multi-Branch Convolution Module Integrated Deeplabv3+ for Bridge Crack Segmentation. Journal of Intelligent & Robotic Systems, 2022, 106(2): 35-48.

[4] Shaker A M, Maaz M, Rasheed H, et al. U-Net+++: Delving into Efficient and Accurate 3D Medical Image Segmentation. IEEE Transactions on Medical Imaging, 2024, 43(7): 2456-2469.

[5] Chen J, Lu Z, Yu Q, et al. TransU-Net: Transformers Make Strong Encoders for Medical Image Segmentation. Medical Image Analysis, 2022, 78: 102381.

[6] Li Q, Wang H, Zhang S. LM-SAU-Net: Lightweight Unet with Depthwise Separable Convolution for Skin Lesion Segmentation. Computational Biology and Chemistry, 2025, 112: 108021.

[7] Xie L, Zhang Y, Liu C. U-Shaped Deformable Transformer for Subarachnoid Hemorrhage Image Segmentation. IEEE Journal of Biomedical and Health Informatics, 2024, 28(4): 987-998.

[8] Hang L, Li J, Wang P. Fundus blood vessel segmentation algorithm based on attention-enhanced Res-U-Net. Journal of Image and Graphics, 2024, 29(5): 1123-1134.

[9] Li M, Zhao Y, Chen X. Application of dual attention fusion U-Net in brain MRI lesion segmentation. Journal of Electronics & Information Technology, 2023, 45(8): 1890-1898.

[10] Wang H, Chen M, Li L. Research on lightweight CBAM-U-Net in dermoscopic image segmentation. Application Research of Computers, 2025, 42(3): 876-881.

[11] Liu J, Zhang H, Wang L. Cross-scale attention U-Net for liver CT tumor segmentation. Control and Decision, 2024, 39(6): 1456-1463.