基于Unet的阿尔兹海默症病灶分割模型
Unet-Based Model of Alzheimer’s Disease Lesion Segmentation
DOI: 10.12677/CSA.2022.121019, PDF,    科研立项经费支持
作者: 徐 超, 王卓薇, 刘晓东：广东工业大学，计算机学院，广东 广州
关键词: 医学图像；语义分割；CBAM；SENet；Unet；Medical Image； Semantic Segmentation； CBAM； SENet； Unet
摘要: 由于人脑的结构比较复杂，所以如何准确的提取分割部位的特征是医学图像语义分割的一个关键点。本文使用Unet网络作为基本框架，并在特征提取过程中引入了注意力机制CBAM，在Unet的Skip-connection过程中引入了SENet。通过这些方法从全局增强分割部位的语义信息并降低其他部位的语义信息。本文使用相同的设备和数据分别在Unet、Unet + CBAM、Unet + SENet以及本文提出的模型进行了实验，得到对应的平均Dice分别对应为0.680、0.703、0.706、0.736。实验表明，本文提出的方法对阿尔兹海默症病灶分割的性能有显著提升。
Abstract: Because the structure of the human brain is relatively complex, how to accurately extract the fea-tures of the segmented part is a key point in the semantic segmentation of medical images. This paper uses Unet network as the basic model framework, and introduces the attention mechanism CBAM in the feature extraction process, and utilizes SEnet in the Skip-connection process of Unet. Through these methods, the semantic information of segmented parts is globally enhanced and the semantic information of other parts is reduced. We compare the proposed method with Unet, Unet + CBAM, and Unet + SENet on the same equipment and data, and the corresponding average Dice is 0.736, 0.680, 0.703, 0.706, respectively. Experiments show that the proposed method can significantly improve the performance of Alzheimer’s disease lesion segmentation.
文章引用：徐超, 王卓薇, 刘晓东. 基于Unet的阿尔兹海默症病灶分割模型[J]. 计算机科学与应用, 2022, 12(1): 178-186. https://doi.org/10.12677/CSA.2022.121019

参考文献

[1] Wen, J., Thibeau-Sutre, E., Diaz-Melo, M., et al. (2020) Convolutional Neural Networks for Classification of Alz-heimer’s Disease: Overview and Reproducible Evaluation. Medical Image Analysis, 63, Article ID: 101694. [Google Scholar] [CrossRef] [PubMed]
[2] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolu-tional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 3431-3440. [Google Scholar] [CrossRef] 
[3] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Con-volutional Networks for Biomedical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 234-241. [Google Scholar] [CrossRef] 
[4] Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., et al. (2016) 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 424-432. [Google Scholar] [CrossRef] 
[5] Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., et al. (2018) Unet++: A Nested U-Net Architecture for Medical Image Segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, Cham, 3-11. [Google Scholar] [CrossRef] [PubMed]
[6] Huang, H., Lin, L., Tong, R., et al. (2020) Unet 3+: A Full-Scale Connected Unet for Medical Image Segmentation. ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, 4-8 May 2020, 1055-1059. [Google Scholar] [CrossRef] 
[7] Isensee, F., Jäger, P.F., Full, P.M., et al. (2020) nnU-net for Brain Tumor Segmentation. In: International MICCAI Brainlesion Workshop, Springer, Cham, 118-132. [Google Scholar] [CrossRef] 
[8] Li, X., Chen, H., Qi, X., et al. (2018) H-Dense UNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes. IEEE Transactions on Medical Imaging, 37, 2663-2674. [Google Scholar] [CrossRef] 
[9] Alom, M.Z., Yakopcic, C., Hasan, M., et al. (2019) Recurrent Residual U-Net for Medical Image Segmentation. Journal of Medical Imaging, 6, Article ID: 014006. [Google Scholar] [CrossRef] 
[10] Wang, F., Jiang, M., Qian, C., et al. (2017) Residual Attention Network for Image Classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 3156-3164. [Google Scholar] [CrossRef] 
[11] Nie, D., Gao, Y., Wang, L., et al. (2018) Asdnet: Attention Based Semi-Supervised Deep Networks for Medical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 370-378. [Google Scholar] [CrossRef] 
[12] Sinha, A. and Dolz, J. (2019) Multi-Scale Guided Attention for Medical Image Segmentation.
[13] Khosravan, N., Mortazi, A., Wallace, M., et al. (2019) Pan: Projective Adver-sarial Network for Medical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 68-76. [Google Scholar] [CrossRef] [PubMed]
[14] Son, J., Park, S.J. and Jung, K.H. (2017) Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks.
[15] Xue, Y., Xu, T., Zhang, H., et al. (2018) SegAN: Adversarial Network with Multi-Scale L1 Loss for Medical Image Segmentation. Neuroinformatics, 16, 383-392. [Google Scholar] [CrossRef] [PubMed]
[16] Woo, S., Park, J., Lee, J.Y., et al. (2018) CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, 8-14 Sep-tember 2018, 3-19. [Google Scholar] [CrossRef] 
[17] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141. [Google Scholar] [CrossRef]