计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 620-624.doi: 10.11896/jsjkx.201200252
孙荣荣1, 单飞2, 叶雯2
SUN Rong-rong1, SHAN Fei2, YE Wen2
摘要： 研究COVID-19低剂量CT图像质量评价算法具有重要意义,但基于深度学习的方法随着网络层数的增加会出现梯度消失问题,针对此问题,文中提出了基于混合域注意力的DenseNet算法。DenseNet通过特征重用和网络的紧密连接,在减少参数的同时解决了梯度消失问题;基于人眼的注意力机制,将自下至上和自上而下结构相结合以实现空间注意力;基于人眼视觉具有多通道特性,针对空间域注意力忽略通道域中的信息,研究混合域注意力,并将其引入至DenseNet。分别用斯皮尔曼等级次序相关系数、皮尔逊线性相关系数来衡量客观评价方法的测试结果与主观评价之间的一致性。实验结果表明,所提方法可以较好地模拟人类的视觉特性,更加准确地对COVID-19低剂量CT进行质量评价,评价结果与人类视觉主观感受有较好的一致性。
中图分类号:
| [1]CHENG J Y,CHEN F,ALLEY M T,et al.Highly Scalable Image Reconstruction Using Deep Neural Networks with Bandpass Filtering[J].arXiv:1805.03300,2018. [2]KÜSTNER T,LIEBGOTT A,MAUCH L,et al.AutomatedReference-Free Detection of Motion Artifacts in Magnetic Resonance Images[J].Magnetic Resonance Materials in Physics,Biology and Medicine,2018,31(2):243-256. [3]MARDANI M,GONG E,CHENG J Y,et al.Deep Generative Adversarial Neural Networks for Compressive Sensing MRI[J].IEEE Transactions on Medical Imaging,2019,38(1):167-179. [4]SZEGEDY C,WEI L,YANGQING J,et al.Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2015:1-9. [5]BOSSE S,MANIRY D,MÜLLER K R,et al.Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment[J].IEEE Transactions on Image Processing,2018,27(1):206-219. [6]GAO F,YU J,ZHU S,et al.Blind image quality prediction by exploiting multi-level deep representations[J].Pattern Recognition,2018,81:432-442. [7]FAN C,ZHANG Y,FENG L,et al.No Reference Image Quality Assessment based on Multi-Expert Convolutional Neural Networks[J].IEEE Access,2018,6:8934-8943. [8]GU J,MENG G,REDI J A,et al.Blind Image Quality Assessment via Vector Regression and Object Oriented Pooling[J].IEEE Transactions on Multimedia,2018,20(5):1140-1153. [9]SZEGEDY C,IOFFE S,VANHOUCKE V,et al.Inception v4,inception resnet and the impact of residual connections on lear-ning[C]//The AAAI Conference on Artificial Intelligence,2017:4278-4284. [10]SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016:2818-2826. [11]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA,2016:770-778. [12]WU P,LIN G Q,GUO Y R,et al.Self-learning sparse denseNet image classification method[J].Journal of Signal Processing,2019,35(10):1747-1752. [13]HUANG G,LIU Z,WEINBERGER K Q,et al.Densely connected convolutional networks[C]//CVPR.2017. [14]IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proc of the 32nd International Conference on Machine Learning.2015:448-456. [15]GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifierneural networks[C]//Proc of the 14th International Conference on Artificial Intelligence and Statistics.Piscataway,NJ:IEEE Press,2011:315-323. [16]SHEIKH H R,BOVIK A C.Image information and visual quality [J].IEEE Trans.Image Process.2006,15(2):430-444. |
| [1] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
| [2] | 刘汉卿, 康晓东, 高万春, 李博, 王亚鸽, 张华丽, 白放. 基于多模型的COVID-19传播研究 Research on Propagation of COVID-19 Based on Multiple Models 计算机科学, 2021, 48(6A): 196-202. https://doi.org/10.11896/jsjkx.201100086 |
| [3] | 李一萌, 李成海, 宋亚飞, 王坚. 基于Attention-DenseNet-BC的恶意软件家族分类方法 Method of Malware Family Classification Based on Attention-DenseNet-BC Model Mechanism 计算机科学, 2021, 48(10): 308-314. https://doi.org/10.11896/jsjkx.210200166 |
| [4] | 骆岩红. CT图像重建滤波反投影算法中指数滤波器的研究 Study on Exponential Filter of Filter Back Projection Algorithm for CT Image Reconstruction 计算机科学, 2014, 41(Z6): 220-223. |
| [5] | 陈刚,吕煊,王志成,陈宇飞. 肺CT图像的血管骨架化方法 Vessel Skeletonization Method for Lung CT Images 计算机科学, 2013, 40(5): 274-278. |
| [6] | . 面向RP的工业CT切片数据格式转换软件开发 计算机科学, 2008, 35(1): 263-265. |
|
||
首页