| 182 | 0 | 29 |
| 下载次数 | 被引频次 | 阅读次数 |
视网膜血管密集且不规则分布，许多毛细血管融入背景，对比度较低，导致视网膜血管分割非常复杂。基于编码器-解码器的视网膜血管分割网络由于多次编码和解码，会导致细节特征的不可逆损失，进而导致血管分割错误。针对这些问题，提出一种用于视网膜血管分割的多尺度细节特征融合网络（multi-scale detail feature fusion network,MDFNet）。为了确保在精细血管分割过程中有效提取复杂特征，构建细节增强编码器（detail-enhanced encoder,DEE）模块以增强细节表示能力；引入动态解码器（dynamic decoder,DYD）模块，在解码过程中保留空间信息，减少上采样操作引起的信息损失；采用多尺度特征融合（multi-scale feature fusion,MFF）模块来融合编码和解码过程中的特征图，以实现多尺度上下文信息的有效聚合。将MDF-Net算法与其他9种算法在DRIVE、CHASEDB1、STARE数据集上进行对比实验。实验结果表明：MDF-Net算法在DRIVE、CHASEDB1和STARE数据集上的灵敏度（sensitivity,Sen）值分别为0.825 0、0.880 9和0.863 4，曲线下面积（area under the curve,AUC）值分别为0.988 5、0.990 8和0.990 9,MDF-Net在视网膜血管分割方面表现出卓越的性能。
Abstract：The segmentation of retinal vessels is highly challenging because retinal vessels are densely and irregularly distributed with many capillaries blending into the background, exhibiting low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding operations, leading to incorrect vessel segmentation. To solve these issues, we propose a multi-scale detail feature fu sion network(MDF-Net) for retinal vessel segmentation. This network incorporates a detail-enhanced encoder(DEE)module to enhance the representation of intricate details, ensuring effective retention of complex features during the segmentation of fine vessels. The dynamic decoder(DYD) module is introduced to preserve spatial information during the decoding process and minimize the information loss caused by upsampling operations. The multi-scale feature fusion(MFF) module fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual infor mation. The experiments on the DRIVE, CHASEDB1, and STARE datasets reveal that MDF-Net achieves sensitivity(Sen)values of 0.825 0, 0.880 9, and 0.863 4, as well as area under the curve(AUC) values of 0.988 5, 0.990 8, and 0.990 9,respectively. These results demonstrate that MDF-Net significantly outperforms existing algorithms in retinal vessel segmentation.
[1]侯向丹，李紫宇，牛敬钰，等.结合注意力机制和多路径U-Net的视网膜血管分割[J].计算机辅助设计与图形学学报，2023,35(1):55-65.
[2]汪恩惠，余艳梅，杜佳成，等.基于MLDCSAU-Net的视网膜图像血管分割算法[J].现代计算机，2024,30(2):44-48.
[3] RONNEBERGER O,FISCHER P,BROX T. U-net:convolutional networks for biomedical image segmentation[C]//Lecture Notes in Computer Science. Cham:Springer International Publishing,2015:234-241.
[4] YUE K J,ZOU B J,CHEN Z L,et al. Retinal vessel segmentation using dense U-net with multiscale inputs[J]. Journal of Medical Imaging,2019,6(3):034004.
[5] 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,2020,39(6):1856-1867.
[6] HUANG H M,LIN L F,TONG R F,et al. UNet 3:a fullscale connected UNet for medical image segmentation[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and SignalProcessing(ICASSP).Barcelona:IEEE,2020:1055-1059.
[7] ZHANG M,YU F,ZHAO J,et al. BEFD:boundary enhancement and feature denoising for vessel segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer,2020:775-785.
[8] GUO C L,SZEMENYEI M,YI Y G,et al. SA-UNet:spatial attention U-net for retinal vessel segmentation[C]//2020 25th International Conference on Pattern Recognition(ICPR). Milan:IEEE,2021:1236-1242.
[9] YANG B,QIN L,PENG H,et al. SDDC-Net:a U-shaped deep spiking neural P convolutional network for retinal vessel segmentation[J].Digital Signal Processing,2023,136:104002.
[10]ZHONG X,ZHANG H B,LI G L,et al. Do you need sharpened details? Asking MMDC-Net:multi-layer multi-scale dilated convolution network for retinal vessel segmentation[J].Computers in Biology and Medicine,2022,150:106198.
[11]HUANG J P,LIN Z F,CHEN Y Y,et al. DBFU-Net:double branch fusion U-Net with hard example weighting train strategy to segment retinal vessel[J]. PeerJ Computer Science,2022,8:e871.
[12]OKTAY O,SCHLEMPER J,LE FOLGOC L,et al. Attention U-net:learning where to look for the pancreas[EB/OL].[2024-05-13].2018:arXiv:1804.03999. http：//arxiv.org/abs/1804.03999.
[13]ZHUANG J T. LadderNet:multi-path networks based on UNet for medical image segmentation[EB/OL].[2024-05-13].2018:arXiv:1810.07810. http：//arxiv.org/abs/1810.07810.
[14] WU H S,WANG W,ZHONG J F,et al. SCS-net:a scale and context sensitive network for retinal vessel segmentation[J]. Medical Image Analysis,2021,70:102025.
[15]ZHANG H B,ZHONG X,LI G L,et al. BCU-Net:bridging ConvNeXt and U-Net for medical image segmentation[J].Computers in Biology and Medicine,2023,159:106960.
[16]STAAL J,ABRAMOFF M D,NIEMEIJER M,et al. Ridgebased vessel segmentation in color images of the retina[J].IEEE Transactions on Medical Imaging,2004,23(4):501-509.
[17]HOOVER A,KOUZNETSOVA V,GOLDBAUM M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response[J]. IEEE Transactions on Medical Imaging,2000,19(3):203-210.
[18] OWEN C G,RUDNICKA A R,MULLEN R,et al. Measuring retinal vessel tortuosity in 10-year-old children:validation of the Computer-Assisted Image Analysis of the Retina(CAIAR)program[J]. Investigative Ophthalmology&Visual Science,2009,50(5):2004-2010.
基本信息:
DOI：10.19573/j.issn2095-0926.202403010
中图分类号:R774.1;TP391.41
引用信息:
[1]蔡鹏飞,李碧原,孙高伟等.MDF-Net：一种多尺度细节特征融合的视网膜血管分割算法[J].天津职业技术师范大学学报,2024,34(03):64-72.DOI:10.19573/j.issn2095-0926.202403010.
基金信息:
天津市自然科学基金资助项目（2021FQ-0027）; 天津市教委科研计划项目（2020KJ124）; 天津职业技术师范大学科研启动项目（41401-KRKC012007）