| 1,152 | 3 | 115 |
| 下载次数 | 被引频次 | 阅读次数 |
随着医疗需求的持续增长，深度学习技术在医学图像自动分割领域展现出巨大的潜力。空间数据智能的发展为医学图像的精确分割提供了新的解决思路。U-Net作为医学图像分割领域最具影响力的网络架构，自2015年提出以来在各类医学影像任务中得到了广泛应用，其独特的编码器-解码器结构设计不仅为后续研究奠定了基础范式，更催生了大量改进网络。系统梳理了U-Net架构的重要发展里程碑：ResUNet通过残差连接解决了深层网络训练困难的问题，Attention-UNet引入自适应注意力机制提升了在跳跃连接中的特征选择精确度，而TransUNet和Swin-UNet则代表了将现代Transformer引入医学图像分割的2个关键阶段，展现了卷积神经网络(Convolutional Neural Network, CNN)与Transformer融合的巨大潜力。通过分析这些代表性网络的架构创新和性能突破，揭示了医学图像分割技术从纯CNN架构向CNN-Transformer混合架构演进的发展趋势。此外，探讨了现有技术面临的挑战，对未来空间数据智能的发展方向提供了见解，为该领域的进一步研究提供了参考。
Abstract：With the increasing demands in healthcare, deep learning technologies have shown tremendous potential in the field of automatic medical image segmentation. The advancement in spatial data intelligence provides novel solutions for achieving high-precision segmentation in medical imaging. As the most influential/prominent network architecture, U-Net has been widely applied across various medical imaging tasks since its introduction in 2015. Its distinctive encoder-decoder structure design not only establishes a fundamental paradigm for subsequent research but also has inspired numerous network improvements. A systematic review of key advancements in U-Net architecture development is provided. ResUNet addresses the training challenges in deep networks by incorporating residual connections, which enhances model stability and convergence. Attention-UNet improves feature selection accuracy within the skip connections by introducing adaptive attention mechanisms. TransUNet and Swin-UNet represent two crucial stages in incorporating modern Transformer architectures into medical image segmentation, demonstrating the significant potential of CNN-Transformer fusion for improving feature representation and segmentation accuracy. The evolutionary trend of medical image segmentation technology is highlighted from conventional CNN-based architectures to CNN-Transformer hybrid architectures. Additionally,the challenges faced by existing technologies are addressed and insights into future development/research directions are provided,providing a comprehensive reference for further research in this field.
[1] 郑彩侠，张同舟，孙长江，等.图像分割方法在医学领域中的应用[J].中国医疗设备，2018,33(6):1-5.
[2] 田娟秀，刘国才，谷珊珊，等.医学图像分析深度学习方法研究与挑战[J].自动化学报，2018,44(3):401-424.
[3] RONNEBERGER O,FISCHER P,BROX T.U-Net:Con-volutional Networks for Biomedical Image Segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.Munich:Springer,2015:234-241.
[4] LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston:IEEE,2015:3431-3440.
[5] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.Unet++:A Nested U-Net Architecture for Medical Image Segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada:Springer,2018:3-11.
[6] ZHANG Z X,LIU Q J,WANG Y H,et al.Road Extraction by Deep Residual U-Net[J].IEEE Geoscience and Remote Sensing Letters,2018,15(5):749-753.
[7] VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.New York:ACM,2017:6000-6010.
[8] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An Image Is Worth 16×16 Words:Transformers for Image Recognition at Scale[EB/OL].(2020-10-22)[2024-05-10].https://arxiv.org/abs/2010.11929.
[9] 王金祥，付立军，尹鹏滨，等.基于CNN与Transformer的医学图像分割[J].计算机系统应用，2023,32(4):141-148.
[10] GU A,DAO T.Mamba:Linear-time Sequence Modeling with Selective State Spaces[EB/OL].(2023-12-01)[2024-05-11].https://arxiv.org/abs/2312.00752.
[11] LITJENS G,KOOI T,BEJNORDI B E,et al.A Survey on Deep Learning in Medical Image Analysis[J].Medical Image Analysis,2017,42:60-88.
[12] JIN D K,XU Z Y,TANG Y B,et al.CT-realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2018.Granada:Springer,2018:732-740.
[13] LI X M,CHEN H,QI X J,et al.H-DenseUNet:Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes[J].IEEE Transactions on Medical Imaging,2018,37(12):2663-2674.
[14] ISENSEE F,JAEGER P F,KOHL S A A,et al.nnU-Net:A Self-configuring Method for Deep Learning-based Biomedical Image Segmentation[J].Nature Methods,2020,18(2):203-211.
[15] HESAMIAN M H,JIA W J,HE X J,et al.Deep Learning Techniques for Medical Image Segmentation:Achievements and Challenges[J].Journal of Digital Imaging,2019,32(4):582-596.
[16] ALOM M Z,YAKOPCIC C,HASAN M,et al.Recurrent Residual U-Net for Medical Image Segmentation[J].Journal of Medical Imaging,2019,6(1):014006.
[17] HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:770-778.
[18] XIAO X,LIAN S,LUO Z M,et al.Weighted Res-UNet for High-quality Retina Vessel Segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education (ITME).Hangzhou:IEEE,2018:327-331.
[19] HOU Q M,LEE H L.Kidney and Kidney Tumour Segmentation in CT Images [EB/OL].(2022-12-26)[2024-05-11].https://arxiv.org/abs/2212.13034.
[20] ZHANG J W,JIN Y C,XU J L,et al.MDU-Net:Multi-scale Densely Connected U-Net for Biomedical Image Segmentation[EB/OL].(2018-12-04)[2024-05-11].https://arxiv.org/pdf/1812.00352v2.
[21] IBTEHAZ N,RAHMAN M S.MultiResUNet:Rethinking The U-Net Architecture for Multimodal Biomedical Image Segmentation[J].Neural Networks,2020,121:74-87.
[22] OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention U-Net:Learning Where to Look for the Pancreas[EB/OL].(2018-04-11)[2024-03-11].https://arxiv.org/abs/1804.03999.
[23] SCHLEMPER J,OKTAY O,SCHAAP M,et al.Attention Gated Networks:Learning to Leverage Salient Regions in Medical Images[J].Medical Image Analysis,2019,53:197-207.
[24] HUANG H M,LIN L F,TONG R F,et al.UNet 3+:A Full-scale Connected UNet for Medical Image Segmentation[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).Barcelona:IEEE,2020:1055-1059.
[25] WANG J D,SUN K,CHENG T H,et al.Deep High-resolution Representation Learning for Visual Recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(10):3349-3364.
[26] LI S Y,DONG M,DU G M,et al.Attention Dense-U-Net for Automatic Breast Mass Segmentation in Digital Mammogram[J].IEEE Access,2019,7:59037-59047.
[27] CHEN L C,ZHU Y K,PAPANDREOU G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV).Munich:Springer,2018:833-851.
[28] CHEN J N,LU Y Y,YU Q H,et al.TransUNet:Transformers Make Strong Encoders for Medical Image Segmentation[EB/OL].(2021-02-08)[2024-03-11].https://arxiv.org/abs/2102.04306.
[29] QU L H,LIU S L,WANG M N,et al.Transfuse:A Unified Transformer-based Image Fusion Framework[EB/OL].(2022-01-19)[2024-05-10].https://arxiv.org/abs/2201.07451.
[30] MARINOV Z,J?GER P F,EGGER J,et al.Deep Interactive Segmentation of Medical Images:A Systematic Review and Taxonomy [J].IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2024,46(12):10998-11018.
[31] MANZARI O N,KALEYBAR J M,SAADAT H,et al.BEFUnet:A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation[EB/OL].(2024-02-13)[2024-05-12].https://arxiv.org/abs/2402.08793.
[32] WANG X L,GIRSHICK R,GUPTA A,et al.Non-local Neural Networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7794-7803.
[33] LIU Z,LIN Y T,GAO Y,et al.Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal:IEEE,2021:9992-10002.
[34] XU S W,SHAO Z Y.An Improved Faster RCNN Based on Swin Transformer for Surface Defect Detection of Metal Workpieces[C]//Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering.Xiamen:ACM,2023:120-125.
[35] ZHANG B W,GU S Y,ZHANG B,et al.StyleSwin:Transformer-based GAN for High-resolution Image Generation[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).New Orleans:IEEE,2021:11294-11304.
[36] XIONG Z N,WANG C X,LI Y,et al.Swin-Pose:Swin Transformer Based Human Pose Estimation[C]//2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR).[S.l.]:IEEE,2022:228-233.
[37] CAO H,WANG Y Y,CHEN J,et al.Swin-Unet:Unet-like Pure Transformer for Medical Image Segmentation[EB/OL].(2021-05-12)[2024-03-22].https://arxiv.org/abs/2105.05537.
[38] GAO Y H,ZHOU M,METAXAS D N,et al.UTNet:A Hybrid Transformer Architecture for Medical Image Segmentation[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021.Strasbourg:Springer,2021:61-71.
[39] DIAKOGIANNIS F L,WALDNER F,CACCETTA P,et al.ResUNet-a:A Deep Learning Framework for Semantic Segmentation of Remotely Sensed Data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,162:94-114.
[40] MICHAEL Y,EVIS S,SCH?NLIEB C B,et al.Focus U-Net:A Novel Dual Attention-gated CNN for Polyp Segmentation During Colonoscopy[J].Computers in Biology and Medicine,2021,137:104815.
[41] DUMITRU R G,PETELEAZA D,CRACIUN C.Using DUCK-Net for Polyp Image Segmentation[J].Scientific Reports,2023,13(1):9803.
[42] FU S H,LU Y Y,WANG Y,et.al.Domain Adaptive Relational Reasoning for 3D Multi-organ Segmentation[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2020.Lima:Springer,2020:656-666.
[43] JIN Q G,MENG Z P,PHAN T D,et al.DUNet:A Deformable Network for Retinal Vessel Segmentation[J].Knowledge-Based Systems,2019,178:149-162.
[44] HASAN S M K,LINTE C A.A Modified U-Net Convolutional Network Featuring a Nearest-neighbor Re-sampling-based Elastic Transformation for Brain Tissue Characterization and Segmentation[C]//2018 IEEE Western New York Image Signal Processing Workshop (WNY ISPW).New York:IEEE,2018:1-5.
[45] KAKEYA H,OKADA T,OSHIRO Y.3D U-JAPA-Net:Mixture of Convolutional Networks for Abdominal Multi-organ CT Segmentation[C]//Medical Image Computing and Computer Assisted Intervention.Granada:Springer,2018:426-433.
[46] LI S,TSO G R F,HE K J.Bottleneck Feature Supervised U-Net for Pixel-wise Liver and Tumor Segmentation[J].Expert Systems with Applications,2020,145:113131.
[47] ZHANG H,ZHU H Q,LING X F.Polar Coordinate Sampling-based Segmentation of Overlapping Cervical Cells Using Attention U-Net and Random Walk[J].Neurocomputing,2020,383:212-223.
[48] COLONNA A,SCARPA F,RUGGERI A.Segmentation of Corneal Nerves Using a U-Net-based Convolutional Neural Network[C]//Computational Pathology and Ophthalmic Medical Image Analysis.Granada:Springer,2018:185-192.
[49] SIDDIQUE N,PAHEDING S,ELKIN C P,et al.U-Net and Its Variants for Medical Image Segmentation:A Review of Theory and Applications[J].IEEE Access,2021,9:82031-82057.
基本信息:
DOI：
中图分类号:R-05;TP18;TP391.41
引用信息:
[1]刘紫权,史旭阳,胡海等.基于U-Net医学图像智能分割的网络结构演变[J].无线电工程,2024,54(12):2765-2779.
基金信息:
四川省科技计划(2024NSFSC2040); 教育部高校产学研创新基金(2023IT257); 成都市技术创新研发项目(2024-YF05-01130-SN); 西南科技大学博士基金项目(23zx7136,23zx7135)~~