|
|
基于深度学习的肺炎影像分割研究
|
Abstract:
为有效地阻断新型冠状病毒肺炎(COVID-19)疫情传播，如何快速准确地诊断出COVID-19患者对于疫情防控至关重要。计算机断层扫描(CT)技术是诊断COVID-19患者的最有效手段之一，为辅助医生进行准确和快速的诊断，需要将COVID-19患者CT图像中病变区域分割出来。近年来，深度学习在医学图像分割中的应用越来越广泛，本文以U-Net语义分割模型为基础框架，针对U-Net模型在训练过程中出现的神经网络性能退化问题，在编码器中运用了在ImageNet上预训练好的Resnet网络，对CT图像进行特征提取。在解码器中引入注意力门机制抑制图像中的无关区域，突出病变区域以进一步提高分割的精度。通过在相同数据集上的对比验证，结果表明，该方法具有良好的分割性能，能有效分割新冠肺炎病变区域。
In order to effectively block the spread of the novel coronavirus disease 2019 (COVID-19), how to quickly and accurately diagnose COVID-19 patients is crucial for epidemic prevention and control. Computed tomography (CT) is one of the most effective methods for the diagnosis of COVID-19 patients. In order to assist doctors in accurate and rapid diagnosis, it is necessary to segment the lesion areas in CT images of COVID-19 patients. In recent years, the application of deep learning in medical image segmentation has become more and more widespread. In this paper, the U-Net semantic segmentation model is taken as the basic framework, and the pre-trained Resnet network on ImageNet is used in the encoder to extract features from CT images in order to solve the problem of neural network performance degradation in the training process of U-NET model. An attention gate mechanism is introduced into the decoder to suppress irrelevant regions in the image and highlight the diseased regions to further improve the segmentation accuracy. Through comparison and verification on the same data sets, the results show that the proposed method has good segmentation performance and can effectively segment the lesion region of COVID-19.
| [1] | Sharif Razavian, A., Azizpour, H., Sullivan, J. and Carlsson, S. (2014) CNN Features Off-the-Shelf: An Astounding Baseline for Recognition. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, 23-28 June 2014, 806-813. https://doi.org/10.1109/CVPRW.2014.131 |
| [2] | Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolutional Networks for Semantic Segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 3431-3440.
https://doi.org/10.1109/CVPR.2015.7298965 |
| [3] | Ronneberger, O., Fischer, P., & Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W. and Frangi, A., Eds., Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015. Lecture Notes in Computer Science, Vol. 9351, Springer, Cham, 234-241.
https://doi.org/10.1007/978-3-319-24574-4_28 |
| [4] | Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N. and Liang, J. (2018) Unet++: A Nested U-Net Architecture for Medical Image Segmentation. Architecture for Medical Image Segmentation. In: Stoyanov, D., Taylor, Z., Carneiro, G., Syeda-Mahmood, T., et al., Eds., Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Lecture Notes in Computer Science, Vol. 11045, Springer, Cham, 3-11.
https://doi.org/10.1007/978-3-030-00889-5_1 |
| [5] | Oktay, O., Schlemper, J., Folgoc, L.L., et al. (2018) Attention U-Net: Learning Where to Look for the Pancreas. ArXiv: 1804.03999. |
| [6] | Lian, S., Li, L., Lian, G., Xiao, X., Luo, Z. and Li, S. (2019). A Global and Local Enhanced Residual U-Net for Accurtate Retinal Vessel Segmentation. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18, 852-862. https://doi.org/10.1109/TCBB.2019.2917188 |
| [7] | 闫文杰. 基于深度学习的肺部CT影像分割算法的研究[D]: [硕士学位论文]. 大连: 大连理工大学, 2019.
https://doi.org/10.26991/d.cnki.gdllu.2019.002214 |
| [8] | 朱海鹏. 一种基于ADID-UNET模型的COVID-19肺部CT图像感染区域分割方法研究[D]: [硕士学位论文]. 汕头: 汕头大学, 2021. https://doi.org/10.27295/d.cnki.gstou.2021.000304 |
| [9] | Kalane, P., Patil, S., Patil, B.P. and Sharma, D.P. (2021) Automatic Detection of COVID-19 Disease Using U-Net Architecture Based Fully Convolutional Network. Biomedical Signal Processing and Control, 67, Article ID: 102518
https://doi.org/10.1016/j.bspc.2021.102518 |
| [10] | 宋瑶, 刘俊. 改进U-Net的新冠肺炎图像分割方法[J]. 计算机工程与应用, 2021, 57(19): 243-251. |
| [11] | Targ, S., Almeida, D. and Lyman, K. (2016) ResNet in ResNet: Generalizing Residual Architectures. ArXiv: 1603.08029. |
| [12] | Zhang, Q., Cui, Z., Niu, X., Geng, S. and Qiao, Y. (2017) Image Segmentation with Pyramid Dilated Convolution Based on ResNet and U-Net. In: Liu, D., Xie, S., Li, Y., Zhao, D. and El-Alfy, E.S., Eds., Neural Information Processing. Lecture Notes in Computer Science, Vol. 10635, Springer, Cham, 364-372. https://doi.org/10.1007/978-3-319-70096-0_38 |
| [13] | Bekele, E., Narber, C. and Lawson, W. (2017) Multi-Attribute Residual Network (MA ResNet) for Soft-Biometrics Recognition in Surveillance Scenarios. 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition, Washington DC, 30 May-3 June 2017. https://doi.org/10.1109/FG.2017.55 |
| [14] | Deng, J., Dong, W., Socher, R., et al. (2009) ImageNet: A Large-Scale Hierarchical Image Database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, 20-25 June 2009, 248-255.
https://doi.org/10.1109/CVPR.2009.5206848 |
| [15] | Ma, J., Wang, Y., An, X., et al. (2020) Towards Efficient COVID-19 CT Annotation: A Benchmark for Lung and Infection Segmentation. ArXiv: 2004.12537. |
