|
|
DouDil-UNet++：基于Dil-UNet++网络的双分支编码器视网膜血管分割网络模型
|
Abstract:
视网膜血管的精确分割对于辅助医生在临床诊断眼科疾病具有重要意义。针对眼底视网膜血管图像中对比度不足、噪声干扰多、血管细节不明显等问题，在Dil-UNet++网络的基础上进行改进提出了DouDil- UNet++网络对视网膜血管进行准确分割。本文提出的DouDil-UNet++网络采用了双分支编码器U形结构，Dil-UNet++作为主分割网络提取视网膜血管图像的空间细节特征信息，Tr-Net作为辅分割网络用于提取视网膜血管图像的全局语义特征信息；在Tr-Net辅分割网络中使用由五层卷积组成的特征序列化模块与使用边缘多头注意力的Transformer特征提取模块来提取图像的全局特征信息；同时使用特征融合模块对主分割网络与辅分割网络提取的特征信息进行聚合。为了验证网络的分割效果，在DRIVE和STARE视网膜血管数据集上进行了分割实验，在DRIVE数据集上该模型的Dice系数、准确度和精确度分别达到87.93%、96.39%和93.52%；在STARE数据集上该模型的Dice系数、准确度和精确度分别达到88.71%、97.79%和87.08%。结果表明本文提出的网络在分割视网膜血管图像任务中有着良好的性能，有一定的使用价值。
A network named DouDil-UNet++ is proposed in this paper to address the challenges of low contrast, high noise, and indistinct vascular details in retinal fundus images, aiming to achieve accurate segmentation of retinal vessels, which is crucial for assisting clinicians in the diagnosis of ophthalmic diseases. The DouDil-UNet++ network is an improved version based on the Dil-UNet++ network and incorporates a dual-branch encoder U-shaped structure. The Dil-UNet++ serves as the main segmentation network to extract spatial detailed features from the retinal vascular images, while the Tr-Net functions as the auxiliary segmentation network to capture global semantic features. The Tr-Net employs a feature sequence module consisting of five convolutional layers and a Transformer feature extraction module with edge multi-head attention to capture the global features of the images. Additionally, a feature fusion module is utilized to aggregate the feature information extracted by the main and auxiliary segmentation networks. To assess the segmentation performance, experiments were conducted on the DRIVE and STARE retinal vessel datasets. On the DRIVE dataset, the model achieves a Dice coefficient of 87.93%, an accuracy of 96.39%, and a precision of 93.52%. On the STARE dataset, the model achieves a Dice coefficient of 88.71%, an accuracy of 97.79%, and a precision of 87.08%.The results indicate that the proposed network exhibits good performance in retinal vessel segmentation tasks, demonstrating its utility and effectiveness.
| [1] | Kadry, S., Rajinikanth, V., Damasevicius, R. and Taniar, D. (2021) Retinal Vessel Segmentation with Slime-Mould-Optimization Based Multi-Scale-Matched-Filter. 2021 Seventh International conference on Bio Signals, Images, and Instrumentation (ICBSII), Chennai, 25-27 March 2021, 1-5. https://doi.org/10.1109/icbsii51839.2021.9445135 |
| [2] | Soares, J.V.B., Leandro, J.J.G., Cesar, R.M., Jelinek, H.F. and Cree, M.J. (2006) Retinal Vessel Segmentation Using the 2-D Gabor Wavelet and Supervised Classification. IEEE Transactions on Medical Imaging, 25, 1214-1222. https://doi.org/10.1109/tmi.2006.879967 |
| [3] | Ala‐Kauhaluoma, M., Ij？s, P., Koskinen, S.M., Nuotio, K., Vikatmaa, P., Silvennoinen, H., et al. (2023) Retinal Vessel Diameters and Microvascular Abnormalities in Patients with Carotid Stenosis before and 6 Months after Carotid Endarterectomy: A Prospective Study. Acta Ophthalmologica, 101, 536-545. https://doi.org/10.1111/aos.15633 |
| [4] | Owen, B.J. and Sathyaprakash, B.S. (1999) Matched Filtering of Gravitational Waves from Inspiraling Compact Binaries: Computational Cost and Template Placement. Physical Review D, 60, Article 022002. https://doi.org/10.1103/physrevd.60.022002 |
| [5] | Shelhamer, E., Long, J. and Darrell, T. (2017) Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 640-651. https://doi.org/10.1109/tpami.2016.2572683 |
| [6] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, Munich, 5-9 October 2015, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [7] | Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N. and Liang, J. (2020) Unet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation. IEEE Transactions on Medical Imaging, 39, 1856-1867. https://doi.org/10.1109/tmi.2019.2959609 |
| [8] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010. |
| [9] | 米文辉, 李鹤, 佘海州. Dil-UNet++: 基于UNet++的多尺度融合视网膜血管分割网络模型[J]. 计算机科学与应用, 2024, 14(1): 54-67. https://doi.org/10.12677/CSA.2024.141007 |
| [10] | Cervan, R.L., Francisco, J. and Perez, R. (2022) Theoretical Model of Attention Deficit with Hyperactivity Disorder I: Operational Definition. Electronic Journal of Research in Educational Psychology, 8, 1303-1338. |
| [11] | Tayeh, T., Aburakhia, S., Myers, R. and Shami, A. (2022) An Attention-Based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series. Machine Learning and Knowledge Extraction, 4, 350-370. https://doi.org/10.3390/make4020015 |
| [12] | 郭峰. 基于改进U型网络的视网膜血管分割方法研究[D]: [硕士学位论文]. 长春: 长春师范大学, 2023. |
| [13] | Li, C., Tan, Y., Chen, W., Luo, X., Gao, Y., Jia, X., et al. (2020) Attention Unet++: A Nested Attention-Aware U-Net for Liver CT Image Segmentation. 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, 25-28 October 2020, 345-349. https://doi.org/10.1109/icip40778.2020.9190761 |
| [14] | Li, X., and Chen, G. (2021) Improving Topology Consistency of Retinal Vessel Segmentation via a Double U-Net with Asymmetric Convolution. In: Su, R., Zhang, YD. and Liu, H., Eds., Proceedings of 2021 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2021), Springer, Singapore, 134-144. https://doi.org/10.1007/978-981-16-3880-0_15 |
| [15] | Yang, X., Li, Z., Guo, Y. and Zhou, D. (2022) DCU-Net: A Deformable Convolutional Neural Network Based on Cascade U-Net for Retinal Vessel Segmentation. Multimedia Tools and Applications, 81, 15593-15607. https://doi.org/10.1007/s11042-022-12418-w |
| [16] | Yan, Z., Yang, X. and Cheng, K. (2019) A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation. IEEE Journal of Biomedical and Health Informatics, 23, 1427-1436. https://doi.org/10.1109/jbhi.2018.2872813 |
| [17] | 刘金. 融合注意力机制和多尺度特征的眼底图像分割方法研究[D]: [硕士学位论文]. 桂林: 桂林电子科技大学, 2023. |
| [18] | Surekcigil Pesch, I., Bestelink, E., de Sagazan, O., Mehonic, A. and Sporea, R.A. (2022) Multimodal Transistors as Relu Activation Functions in Physical Neural Network Classifiers. Scientific Reports, 12, Article No. 670. https://doi.org/10.1038/s41598-021-04614-9 |
| [19] | Heindl, M., Tenbohlen, S., Velásquez, J., et al. (2022) Transformer Modelling Based on Frequency Response Measurements for Winding Failure Detection. Proceedings of the 2010 International Conference on Condition Monitoring and Diagnosis, Tokyo, 6-11 September 2010, 201-204. |
| [20] | 李紫正. 基于U-Net和注意力机制的视网膜眼底图像分割方法研究[D]: [硕士学位论文]. 桂林: 桂林电子科技大学, 2023. |
| [21] | Sun, X., Li, J., Ma, J., Xu, H., Chen, B., Zhang, Y., et al. (2021) Segmentation of Overlapping Chromosome Images Using U-Net with Improved Dilated Convolutions. Journal of Intelligent & Fuzzy Systems, 40, 5653-5668. https://doi.org/10.3233/jifs-201466 |
| [22] | Wei, X., Junwei, T. and Chi, Z. (2023) DC-CBAM-UNet++ Network for Lung Nodule Image Segmentation. Software Guide, 22, 125-130. |
| [23] | Vigneron, V., Maaref, H. and Syed, T.Q. (2021) A New Pooling Approach Based on Zeckendorf’s Theorem for Texture Transfer Information. Entropy, 23, 279. https://doi.org/10.3390/e23030279 |
| [24] | 苏赋, 方东, 王龙业, 等. 基于双解码路径DD-UNet的脑肿瘤图像分割算法[J]. 光电子？激光, 2023, 34(3): 328-336. |
| [25] | Du, H., Zhang, X., Song, G., Bao, F., Zhang, Y., Wu, W., et al. (2023) Retinal Blood Vessel Segmentation by Using the MS-LSDNet Network and Geometric Skeleton Reconnection Method. Computers in Biology and Medicine, 153, Article 106416. https://doi.org/10.1016/j.compbiomed.2022.106416 |
| [26] | Li, B., Wu, F., Liu, S., Tang, J., Li, G., Zhong, M., et al. (2022) CA‐Unet++: An Improved Structure for Medical CT Scanning Based on the Unet++ Architecture. International Journal of Intelligent Systems, 37, 8814-8832. https://doi.org/10.1002/int.22969 |
| [27] | Li, J., Zhang, T., Zhao, Y., et al. (2022) MC-UNet Multi-Module Concatenation Based on U-Shape Network for Retinal Blood Vessels Segmentation. Computational Intelligence and Neuroscience, 2022, Article 9917691. https://doi.org/10.1155/2022/9917691 |
| [28] | Marcellino, Cenggoro, T.W. and Pardamean, B. (2022) UNET++ with Scale Pyramid for Crowd Counting. ICIC Express Letters, 16, 75-82. https://doi.org/10.24507/icicel.16.01.75 |
| [29] | Torbunov, D., Huang, Y., Yu, H., Huang, J., Yoo, S., Lin, M., et al. (2023) UVCGAN: UNet Vision Transformer Cycle-Consistent GAN for Unpaired Image-to-Image Translation. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, 2-7 January 2023, 702-712. https://doi.org/10.1109/wacv56688.2023.00077 |
