计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200119-8.doi: 10.11896/jsjkx.230200119
孙开鑫, 刘斌, 苏曙光
SUN Kaixin, LIU Bin, SU Shuguang
摘要: 医学显微图像分割在临床诊断和病理分析中具有重要应用价值。然而,由于显微图像具有形状、纹理、大小等复杂的视觉特征,因此要精确分割显微图像是一项困难的任务。文中提出了一种新的分割模型UMSTC,该模型基于U型结构,并通过将U-net模型和Swin Transformer模型进行融合来兼顾图像的细节特征和宏观特征,并保持建模完整性。具体来说,UMSTC模型的下采样部分采用Swin Transformer网络来优化其内含的注意力机制,以提取微观和宏观特征;上采样部分基于CNN网络反卷积操作,并通过残差机制接收和融合下采样阶段的特征图,以减小图像合成精度损失。实验结果表明,所提出的UMSTC分割模型比目前主流的医学图像语义分割模型具有更好的分割效果,其中mPA提高了约3%~5%,mIoU提高了约3%~8%,且分割结果具有更高的主观视觉质量和更少的噪点。因此,UMSTC模型在医学显微图像分割领域具有广泛的应用前景。
中图分类号:
[1]WANG F L.Experimental Study on Detecting Diffuse Axonal Injury with FTIR Mapping[D].WuHan:Huazhong University of Science & Technology,2018. [2]LI S X.Study of diffusion tensor imaging and immunohistochemistry on diffuse axonal injury[D].WuHan:Huazhong University of Science & Technology,2012. [3]LEI T,ZHOU W,ZHANG Y,et al.Lightweight v-net for liver segmentation[C]//2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP 2020).IEEE,2020:1379-1383. [4]VALANARASU J M J,PATEL V M.UNeXt:MLP-based Rapid Medical Image Segmentation Network[J].arXiv:2203.04967,2022. [5]CHEN P H C,GADEPALLI K,MACDONALD R,et al.Microscope 2.0:an augmented reality microscope with real-time artificial intelligence integration[J].arXiv:1812.00825,2018. [6]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90. [7]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [8]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017. [9]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2015:3431-3440. [10]CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Deeplab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected crfs[J].IEEE transactions on pattern analysis and machine intelligence,2017,40(4):834-848. [11]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2017:2881-2890. [12]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.2015:234-241. [13]ZHOU Z,SIDDIQUEE M M R,TAJBAKHSH N,et al.A Nested U-Net Architecture for Medical Image Segmentation[J].arXiv:1807.10165,2018. [14]DIAKOGIANNIS F I,WALDNER F,CACCETTA P,et al.ResU-Net-a:A deep learning framework for semantic segmentation of remotely sensed data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,162(1):94-114. [15]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].Advances in neural information processing systems,2017,30. [16]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16x16 words:Transformers for image recognition at scale[J].arXiv:2010.11929,2020. [17]CHEN J,LU Y,YU Q,et al.TransUnet:Transformers make strong encoders for medical image segmentation[J].arXiv:2102.04306,2021. [18]ZHANG Y,LIU H,HU Q.Transfuse:Fusing transformers and cnns for medical image segmentation[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021.2021:14-24. [19]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. |
|