| 453 | 0 | 286 |
| 下载次数 | 被引频次 | 阅读次数 |
生物医学图像分割已成为医学诊断中的关键任务之一。然而，由于组织和器官的复杂形态及其结构的多样性，医学图像分割技术的实际应用面临显著的技术挑战。在传统卷积神经网络(Convolutional Neural Network, CNN)中，最大池化操作常常导致信息的不可逆丢失，尽管引入小波变换在一定程度上改善了这一问题，但小波变换本身也存在局限性。为了解决这一问题，提出了一种基于双树复小波变换(Dual-Tree Complex Wavelet Transform, DTCWT)和U-Net的视网膜血管分割模型——DTCWU-Net。该模型通过引入DTCWT替代传统池化层，双树复小波逆变换(Inverse DTCWT,IDTCWT)替代传统上采样层，显著增强了特征提取能力，尤其在保留图像细节方面表现出色。DTCWU-Net还引入了高低频特征融合注意力(Low and High Feature Fusion Attention, LHFFA)和多尺度门控注意力(Multi-Scale Gate Attention, MSGA)模块，进一步提升分割性能。实验结果表明，DTCWU-Net在DRIVE数据集上取得的准确率(Accuracy, ACC)为0.968 6,受试者工作特征(Receiver Operating Characteristic, ROC)曲线下面积(Area Under the ROC Curve, AUC)为0.986 7,在CHASE＿DB1数据集上取得的ACC为0.975 0,AUC为0.990 3,在STARE数据集上取得的ACC为0.975 7,AUC为0.990 1。在F1、灵敏度(Sensitivity, SE)、ACC和AUC等关键指标上，超越了其他主流方法的表现。通过多模块协同优化，DTCWU-Net显著提高并展现了视网膜血管分割精度与细节恢复能力。
Abstract：Biomedical image segmentation has become one of the key tasks in medical diagnosis. However, due to the complex morphology of tissues and organs and the diversity of their structures, the practical application of medical image segmentation techniques faces significant technical challenges. In traditional Convolutional Neural Network(CNN), the maximum pooling operation often results in irreversible loss of information. Although the incorporation of the wavelet transform mitigates this issue to some extent, the wavelet transform itself also has its own limitations. To solve this problem, a retinal blood vessel segmentation model named DTCWU-Net based on Dual-Tree Complex Wavelet Transform(DTCWT) and U-Net is proposed. The model replaces the traditional pooling layer with DTCWT and traditional upsampling layer with the Inverse DTCWT(IDTCWT). This significantly enhances the feature extraction ability, particularly in preserving image details. DTCWU-Net also introduces Low and High Feature Fusion Attention(LHFFA) and Multi-Scale Gate Attention(MSGA) modules to further improve the segmentation performance. The experimental results show that DTCWU-Net achieved an Accuracy(ACC) of 0.968 6 and an Area Under the ROC(Receiver Operating Characteristic) Curve(AUC) of 0.986 7 on the DRIVE dataset, an ACC of 0.975 0 and an AUC of 0.990 3 on the CHASE＿DB1 dataset, an ACC of 0.975 7 and an AUC of 0.990 1 on the STARE dataset, The proposed model demonstrates superior performance in key metrics when compared to other mainstream methods, including F1, Sensitivity(SE), ACC and AUC. Through the collaborative optimization of multiple modules, DTCWU-Net significantly improves and demonstrates the accuracy of retinal vessel segmentation and the ability to recover details.
[1] ROYCHOWDHURY S,KOOZEKANANI D D,PARHI K K.Blood Vessel Segmentation of Fundus Images by Major Vessel Extraction and Subimage Classification [J].IEEE Journal of Biomedical and Health Informatics,2014,19(3):1118-1128.
[2] STAAL J,ABRAMOFF M D,NIEMEIJER M,et al.Ridge-based Vessel Segmentation in Color Images of the Retina[J].IEEE Transactions on Medical Imaging,2004,23(4):501-509.
[3] TUBA E,MRKELA L,TUBA M.Retinal Blood Vessel Segmentation by Support Vector Machine Classification[C]//2017 27th International Conference Radioelektronika (RADIOELEKTRONIKA).Brno:IEEE,2017:1-6.
[4] RICCIE,PERFETTI R.Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification [J].IEEE Transactions on Medical Imaging,2007,26(10):1357-1365.
[5] CHENG E K,DU L,WU Y.Discriminative Vessel Segmentation in Retinal Images by Fusing Context-aware Hybrid Features[J].Machine Vision and Applications,2014,25:1779-1792.
[6] SOARES J V B,LEANDRO J J G,CESAR R M,et al.Retinal Vessel Segmentation Using the 2-D Gabor Wavelet and Supervised Classification[J].IEEE Transactions on Medical Imaging,2006,25(9):1214-1222.
[7] LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[C]//Fully Convolutional Networks for Semantic Segmentation.Boston:IEEE,2017:640-651.
[8] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//Medical Image Computing and Computer-assisted Intervention-MICCAI.Munich:Springer,2015:234-241.
[9] 季莉.基于全分辨率注意力U-Net神经网络的区域分割方法[J].无线电工程，2023,53(9):1981-1989.
[10] 刘启，张晓蕾，王亚楠.一种基于先验信息和 U-Net 的 SAR 图像海陆分割方法[J].无线电工程，2021,51(12):1471-1476.
[11] 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.
[12] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.UNet++:Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation[J].IEEE Transactions on Medical Imaging,2019,39(6):1856-1867.
[13] HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:770-778.
[14] KUMAR Y,GUPTA B.Retinal Image Blood Vessel Classification Using Hybrid Deep Learning in Cataract Diseased Fundus Images[J].Biomedical Signal Processing and Control,2023,84:104776.
[15] GRAHAM B.Fractional Max-pooling[EB/OL].(2014-12-18) [2025-01-08].https://arxiv.org/abs/1412.6071.
[16] DUAN Y P,LIU F,JIAO L C,et al.SAR Image Segmentation Based on Convolutional-wavelet Neural Network and Markov Random Field [J].Pattern Recognition,2017,64:255-267.
[17] FUJIEDA S,TAKAYAMA K,HACHISUKA T.Wavelet Convolutional Neural Networks[EB/OL].(2018-05-20) [2025-01-08].https://arxiv.org/abs/1805.08620.
[18] YANG K B,LEE J,YANG J.Multi-class Semantic Segmentation of Breast Tissues from MRI Images Using U-Net Based on Haar Wavelet Pooling [J].Scientific Reports,2023,13:11704-11716.
[19] ZHAO C,XIA B,GUO L B,et al.Multi-scale Wavelet Network Algorithm for Pediatric Echocardiographic Segmentation via Feature Fusion[C]//Proceedings of the 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).Nice:IEEE,2021:1402-1405.
[20] LI Q F,SHEN L L.WaveSNet:Wavelet Integrated Deep Networks for Image Segmentation[C]//5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV).Shenzhen:Springer,2022:325-337.
[21] ZENG Y,LI J,ZHAO Z,et al.WET-UNet:Wavelet Integrated Efficient Transformer Networks for Nasopharyngeal Carcinoma Tumor Segmentation [J].Science Progress,2024,107(2):1-23.
[22] ALABA S Y,BALL J E.WCAM:Wavelet Convolutional Attention Module[C]//SoutheastCon 2024.Atlanta:IEEE,2024:854-859.
[23] XIONG W Q,CHEN Z L,LIU Q,et al.PaCaS-WAA:Patch-based Contrastive Semi-supervised Learning with Wavelet Guidance and Adaptive Augmentation for Tumour Segmentation[C]//ICASSP 2024-2024 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).Seoul:IEEE,2024:12941-12945.
[24] LI G Y,LYU J,WANG C Y,et al.WavTrans:Synergizing Wavelet and Cross-attention Transformer for Multi-contrast MRI Super-resolution[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.Singapore:Springer,2022:463-473.
[25] FINDER S E,AMOYAL R,TREISTER E,et al.Wavelet Convolutions for Large Receptive Fields [J].European Conference on Computer Vision (ECCV).Milan:Springer,2024:363-380.
[26] XIANG Y J,HU G S,CHEN M,et al.WMANet:Wavelet-based Multi-scale Attention Network for Low-light Image Enhancement [J].IEEE Access,2024,12:105674-105685.
[27] SELESNICK I W,BARANIUK R G,KINGSBURY N C.The Dual-tree Complex Wavelet Transform[J].IEEE Signal Processing Magazine,2005,22(6):123-151.
[28] HWANG S,HAN D,JUNG C,et al.WaveDH:Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing[EB/OL].(2024-04-02) [2025-01-08].https://arxiv.org/abs/2404.01604.
[29] WANG L Y,SUN Y K.Image Classification Using Convolutional Neural Network with Wavelet Domain Inputs[J].IET Image Processing,2022,16(8):2037-2048.
[30] PRADEEP N R,MANJUNATHA D V,NAPOLEAN A,et al.A New Approach Utilizing DTCWT for Feature Extraction and ANN for Classification to Improve Fingerprint Recognition[J].Engineering Research Express,2025,7(1):015226.
[31] PENG Y P,SONKA M,CHEN D Z.Spectral U-Net:Enhancing Medical Image Segmentation via Spectral Decomposition[EB/OL].(2024-09-13) [2025-01-08].https://arxiv.org/abs/2409.09216.
[32] YANG R,ZHANG S P.Enhancing Retinal Vascular Structure Segmentation in Images with a Novel Design Two-Path Interactive Fusion Module Model[EB/OL].(2024-03-03) [2025-01-08].https://arxiv.org/abs/2403.01362.
[33] KOLAHI S G,CHAHARSOOGHI S K,KHATIBI T,et al.MSA2Net:Multi-scale Adaptive Attention-guided Network for Medical Image Segmentation[EB/OL].(2024-07-31) [2025-01-08].https://arxiv.org/abs/2407.21640.
[34] RAHMAN M M,MUNIR M,MARCULESCU R.EMCAD:Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE,2024:11769-11779.
[35] HWANG C L,YOON K.Multiple Attribute Decision Making[M].Berlin:Springer,1981.
[36] ZHANG Z X,LIU Q J,WANG Y H.Road Extraction by Deep Residual U-Net [J].IEEE Geoscience and Remote Sensing Letters,2018,15(5):749-753.
[37] ALOM M Z,HASAN M,YAKOPCIC C,et al.Recurrent Residual Convolutional Neural Network Based on U-Net (R2U-Net) for Medical Image Segmentation [EB/OL].(2018-02-20) [2025-01-08].https://arxiv.org/abs/1802.06955.
[38] CHEN L C,ZHU Y K,PAPANDREOU G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]//European Conference on Computer Vision (ECCV).Munich:Springer,2018:833-851.
[39] ZHUANG J T.LadderNet:Multi-path Networks Based on U-Net for Medical Image Segmentation [EB/OL].(2018-10-17) [2025-01-08].https://arxiv.org/abs/1810.07810.
[40] SATHANANTHAVATHI V,INDUMATHI G.Encoder Enhanced Atrous (EEA) Unet Architecture for Retinal Blood vessel segmentation [J].Cognitive Systems Research,2021,67:84-95.
[41] WANG S H,LI L,ZHUANG X H.AttU-NET:Attention U-Net for Brain Tumor Segmentation [C]//Proceedings of the International MICCAI Brainlesion Workshop.Singapore:Springer,2022:302-311.
[42] KARAALI A,DAHYOT R,SEXTON D J.DR-VNet:Retinal Vessel Segmentation via Dense Residual UNet[C]//Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence.Paris:Springer,2022:198-210.
[43] WANG B,WANG S P,QIU S,et al.CSU-Net:A Context Spatial U-Net for Accurate Blood Vessel Segmentation in Fundus Images[J].IEEE Journal of Biomedical and Health Informatics,2020,25(4):1128-1138.
[44] 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) [2025-01-08].https:∥arxiv.org/abs/2102.04306.
[45] KUMAR A,AGRAWAL R K,JOSEPH L.IterMiUnet:A Lightweight Architecture for Automatic Blood Vessel Segmentation[J].Multimedia Tools and Applications,2023,82:43207-43231.
[46] NI J J,MU W,PAN A,et al.FSE-Net:Rethinking the Up-sampling Operation in Encoder-Decoder Structure for Retinal Vessel Segmentation[J].Biomedical Signal Processing and Control,2024,90:105861.
[47] DING W P,SUN Y,HUANG J S,et al.RCAR-UNet:Retinal Vessel Segmentation Network Algorithm via Novel Rough Attention Mechanism[J].Information Sciences,2024,657:120007.
[48] LIAO W B,ZHU Y H,WANG X Y,et al.Lightm-UNet:Mamba Assists in Lightweight UNet for Medical Image Segmentation[EB/OL].(2024-03-08) [2025-01-08].https://arxiv.org/abs/2403.05246.
[49] ZOU B J,DAI Y L,HE Q,et al.Multi-label Classification Scheme Based on Local Regression for Retinal Vessel Segmentation[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2020,18(6):2586-2597.
[50] DU X F,WANG J S,SUN W Z.UNet Retinal Blood Vessel Segmentation Algorithm Based on Improved Pyramid Pooling Method and Attention Mechanism[J].Physics in Medicine & Biology,2021,66(17):175013.
[51] KHAN T M,KHAN M A U,REHMAN N U,et al.Width-wise Vessel Bifurcation for Improved Retinal Vessel Segmentation[J].Biomedical Signal Processing and Control,2022,71(Part A):103169.
[52] ORLANDO J I,PROKOFYEVA E,BLASCHKO M B.A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images[J].IEEE Transactions on Biomedical Engineering,2016,64(1):16-27.
[53] LI Y,ZHANG Y,CUI W G,et al.Dual Encoder-based Dynamic-channel Graph Convolutional Network with Edge Enhancement for Retinal Vessel Segmentation[J].IEEE Transactions on Medical Imaging,2022,41(8):1975-1989.
[54] JIN Q G,MENG Z P,PHAM T D,et al.DUNet:A Deformable Network for Retinal Vessel Segmentation[J].Knowledge-Based Systems,2019,178:149-162.
[55] LI L Z,VERMA M,NAKASHIMA Y,et al.IterNet:Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks[C]//2020 IEEE Winter Conference on Applications of Computer Vision (WACV).Snowmass:IEEE,2020:3645-3654.
[56] SAMUEL P M,VEERAMALAI T.VSSC Net:Vessel Specific Skip Chain Convolutional Network for Blood Vessel Segmentation[J].Computer Methods and Programs in Biomedicine,2021,198:105769.
[57] HU J F,WANG H,GAO S B,et al.S-UNet:A Bridge-style U-Net Framework with a Saliency Mechanism for Retinal Vessel Segmentation[J].IEEE Access,2019,7:174167-174177.
[58] LI X,JIANG Y C,LI M L,et al.Lightweight Attention Convolutional Neural Network for Retinal Vessel Image Segmentation[J].IEEE Transactions on Industrial Informatics,2020,17(3):1958-1967.
[59] YANG L,WANG H X,ZENG Q S,et al.A Hybrid Deep Segmentation Network for Fundus Vessels via Deep-learning Framework[J].Neurocomputing,2021,448:168-178.
[60] SHEN X R,XU J J,JIA H B,et al.Self-attentional Microvessel Segmentation via Squeeze-Excitation Transformer Unet[J].Computerized Medical Imaging and Graphics,2022,97:102055.
基本信息:
中图分类号:R774.1;TP391.41
引用信息:
[1]陶寅涵,朱家明,吴军.基于双树复小波变换和U-Net的视网膜血管分割[J].无线电工程,2025,55(06):1161-1176.
基金信息:
国家自然科学基金(62473362)~~