Fusion multi-scale Transformer skin lesion segmentation algorithm

被引:0
作者
Liang L.-M. [1 ]
Zhou L.-S. [1 ]
Yin J. [1 ]
Sheng X.-Q. [2 ]
机构
[1] School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou
[2] School of Computer Science and Engineering, South China University of Technology, Guangzhou
来源
Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2024年 / 54卷 / 04期
关键词
channel attention module; computer application technology; image segmentation; multi-scale fusion module; skin lesions; transformer;
D O I
10.13229/j.cnki.jdxbgxb.20220692
中图分类号
学科分类号
摘要
To address the problem of lack of multi-scale feature extraction in existing skin lesion image segmentation,which leads to lack of detailed information and incorrect segmentation of skin lesion regions,this paper proposes a fusion multi-scale Transformer encoder-decoder network skin lesion segmentation algorithm. First,a hierarchical encoder is constructed using Transformer Block,which analyses the skin lesion region from the perspective of global feature variation at multiple scales. Then,the multi-scale fusion module,channel attention module and concat layer are used to construct the fusion decoder. The multi-scale fusion module fuses shallow network information and deep network information in the hierarchical encoder to enhance the dependency between spatial and semantic information,and the channel attention module can effectively identify channels containing rich feature information and improve the segmentation accuracy of the algorithm. Finally,an expansion module is introduced to recover the image size to meet the practical requirements. The proposed algorithm was experimentally tested on three public datasets,ISBI2016,ISBI2017 and ISIC2018. The pixel accuracies were 96.70%,94.50% and 95.39%,respectively,and the mean intersection over union were 91.69%,85.74% and 89.29%,respectively,with the overall performance of the tested algorithms outperforming existing algorithms.Simulation experiments show that the multi-scale Transformer encoder-decoder network can effectively segment skin lesion images,providing a new window for the diagnosis of modern skin diseases. © 2024 Editorial Board of Jilin University. All rights reserved.
引用
收藏
页码:1086 / 1098
页数:12
相关论文
共 27 条
  • [1] Jin Q, Cui H, Sun C, Et al., Cascade knowledge diffusion network for skin lesion diagnosis and segmentation, Applied Soft Computing, 99, (2021)
  • [2] Sarker M M K, Rashwan H A, Akram F, Et al., SLSNet: skin lesion segmentation using a lightweight generative adversarial network, Expert Systems with Applications, 183, (2021)
  • [3] Ouyang Ji-hong, Guo Ze-qi, Liu Si-guang, Dualbranch hybrid attention decision net for diabetic retinopathy classification, Journal of Jilin University (Engineering and Technology Edition), 52, 3, pp. 648-656, (2022)
  • [4] Wang Xue, Li Zhan-shan, Lyu Ying-da, Medical image segmentation based on multi⁃scale contextaware and semantic adaptor, Journal of Jilin University(Engineering and Technology Edition), 52, 3, pp. 640-647, (2022)
  • [5] Wang Sheng-sheng, Chen Jing-yu, Lu Yi-nan, COVID⁃19 chest CT image segmentation based on federated learning and blockchain, Journal of Jilin University(Engineering and Technology Edition), 51, 6, pp. 2164-2173, (2021)
  • [6] Zhang Heng-liang, Li Qiang, Guan Xin, An improved three-dimensional dual-path brain tumor image segmentation network, Acta Optica Sinica, 41, 3, pp. 54-61, (2021)
  • [7] Shelhamer E, Long J, Darrell T., Fully convolutional networks for semantic segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 4, pp. 640-651, (2016)
  • [8] Ronneberger O, Fischer P, Brox T., U-net: convolutional networks for biomedical image segmentation[C], International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 234-241, (2015)
  • [9] Sarker M, Kamal M, Rashwan H A, Et al., SLSDeep: skin lesion segmentation based on dilated residual and pyramid pooling networks[C], International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 21-29, (2018)
  • [10] Gu R, Wang L, Zhang L., DE-Net: a deep edge network with boundary information for automatic skin lesion segmentation, Neurocomputing, 468, pp. 71-84, (2022)