基于Transformer在腹部多器官图像分割的研究进展
康运成

湖南工业大学生物与医学工程学院，湖南省株洲市，412007；

摘要：腹部多器官图像精准分割在现代临床影像检查、精准诊断和治疗规划中意义至关重要。CNN架构中存在的局部感受野和固有归纳偏置局限，限制其对图像中远程依赖关系的有效建模。近年来，Transformer架构依赖其对全局信息的捕获能力，有助于建模长距离的依赖关系并挖掘语义信息，在生物医学图像分割领域展示出卓越的性能和巨大潜力。在此，对Transformer架构的组成及其在腹部多器官图像分割中的应用进行了全面综述，并对Transformer模型在分割任务中存在的局限不足进行了概括总结，最后对其未来发展趋势及优化路径进行了探讨展望。

关键词：深度学习；Transformer；腹部多器官图像分割；卷积神经网络

参考文献

[1]MINAEE S, BOYKOV Y, PORIKLI F, et al. Image segmentation using deep learning: A survey[J]. IEEE transactions on pattern analysis and machine intelligence, 2021, 44(7): 3523-3542.

[2]GOLAN R, JACOB C, DENZINGER J. Lung nodule detection in CT images using deep convolutional neural networks[C]//2016 international joint conference on neural networks (IJCNN). IEEE, 2016: 243-250.

[3]CHRIST P F, ETTLINGER F, GRÜN F, et al. Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks[J]. arXiv preprint arXiv:1702.05970, 2017.

[4]Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[5]Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arxiv preprint arxiv:2010.11929, 2020.

[6]Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10012-10022.

[7]Huang X, Deng Z, Li D, et al. Missformer: An effective medical image segmentation transformer[J]. arxiv preprint arxiv:2109.07162, 2021.

[8]Chen J, Lu Y, Yu Q, et al. Transunet: Transformers make strong encoders for medical image segmentation[J]. arxiv preprint arxiv:2102.04306, 2021.

[9]Cao H, Wang Y, Chen J, et al. Swin-unet: Unet-like pure transformer for medical image segmentation[C]//European conference on computer vision.Cham:Springer Nature Switzerland, 2022:205-218.