Research on Chest CT Image Classification Method Combining Attention Mechanism and Lightweight Convolutional Neural Network
Wang Wei1, Xu Yuyan1, Wang Xin1*, Huang Wendi1, Yuan Ping2
1(School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410000, China) 2(Changsha Jingwang Information Technology Co., Ltd, Changsha 410000, China)
Abstract CT images of the same disease type can also show differences due to the different severity of the patient′s disease. At present, main clinical diagnosis methods rely on personal ability and past experience of doctors, and the objectivity needs to be enhanced and the efficiency needs to be improved. In view of these problems, we proposed a CT classification network with attention mechanism-parallel lightweight convolutional neural network for CT classification (PC-CTNet). This network mainly consisted of parallel branch channel shuffle (PCS) module and deep-wise efficient shortcut connection (DES) module. PCS module adopted double branches, fused the features under the multi-scale receptive field. DES module used convolution and efficient channel attention to extract effective deep inter-class differentiation information, and alleviated gradient disappearance by shortcut connection. Experiments were conducted on two chest CT datasets, and the results showed that the classification accuracy of the PC-CTNet model reached 98.46% on the collected dataset with 5 988 CT images in different sizes, and 98.75% on the open-source datasets with 194 922 CT images. The performance indicators of PC-CTNet were close to the existing chest CT classification network, and its parameter and computational complexity was about 0.32 M and 75.58 M, respectively, which was 10.17% and 3.21% of the chest CT classification network in the experimental comparison. The proposed network has higher parameter and computational efficiency, can effectively assist doctors in diagnosis and improve diagnostic efficiency and objectivity.
Wang Wei,Xu Yuyan,Wang Xin, et al. Research on Chest CT Image Classification Method Combining Attention Mechanism and Lightweight Convolutional Neural Network[J]. Chinese Journal of Biomedical Engineering, 2024, 43(4): 429-437.
[1] 许敏杰.病毒性肺炎与细菌性肺炎胸部CT特点、临床表现比较分析[J].中国医疗器械信息,2018,24(17):48-50. [2] 吴清海.探讨胸部CT检查在诊断肺炎中的临床意义[J].影像研究与医学应用,2021,5(9):119-120. [3] Iandola FN, Han S, Moskewicz MW, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[EB/OL]. https://arxiv.org/abs/1602.07360, 2016-03-24/2022-11-03. [4] Howard AG, Zhu Menglong, Chen Bo, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. https://arxiv.org/abs/1704.04861,2017-04-17/2022-11-03. [5] Tan Mingxing, Le QV. EfficientNet:Rethinking model scaling for convolutional neural networks[C]// International Conference on Machine Learning. New York: PMLR,2019:6105-6114. [6] Shen Wei, Zhou Mu, Yang Feng, et al. Multi-scale convolutional neu ral networks for lung nodule classification[C]// Proceedings of International Conference on Information Processing in Medical Imaging. Heidelberg: Springer, 2015: 588-599. [7] 张福玲,张少敏,支力佳,等.融合注意力机制和特征金字塔网络的CT图像肺结节检测[J].中国图象图形学报,2021,26(9):2156-2170. [8] 管姝,张骞予,谢红薇,等.CT影像识别的卷积神经网络模型[J].计算机辅助设计与图形学学报,2018,30(8):1530-1535. [9] 王威,胡亿洋,王新,等.针对新型冠状病毒肺炎X射线图像识别的DD-CovidNet模型[J].计算机辅助设计与图形学学报, 2021,33(11):1649-1657. [10] Li Lin, Qin Lixin, Xu Zeguo, et al. Using Artificial intelligence to detect COVID-19 and community-acquired pneumonia based on pulmonary CT: evaluation of the diagnostic accuracy[J]. Radiology,2020, 296(2): E65-E71. [11] Alshazly H, Linse C, Abdalla M, et al. COVID-Nets: deep CNN architectures for detecting COVID-19 using chest CT scans[J]. PeerJ Computer Science, 2021, 7(4): e655. [12] Hou Qibin, Zhou Daquan, Feng Jiashi. Coordinate attention for efficient mobile network design[C]// Proceedings of 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE,2021: 13713-13722. [13] 刘羽,朱文瑜,成娟,等.残差密集注意力网络多模态MR图像超分辨率重建[J].中国图象图形学报,2023,28(1):248-259. [14] Ma Ningning, Zhang Xiangyu, Zheng Haitao, et al. Shufflenet V2: practical guidelines for efficient cnn architecture design[C]// Proceedings of 2018 European Conference on Computer Vision (ECCV). Munich: Springer, Cham,2018: 122-138. [15] Zhang Xiangyu, Zhou Xinyu, Lin Mengxiao, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE,2018 :6848-6856. [16] Zhang Richard. Making convolutional networks shift-invariant again[C]// International Conference on Machine Learning. New York: PMLR,2019: 7324-7334. [17] 汪璟玢,赖晓连,雷晶,等.基于注意力机制的多尺度空洞卷积神经网络模型[J].模式识别与人工智能,2021,34(6):497-508. [18] Howard A, Sandler M, Chen B, et al. Searching for MobileNetV3[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE,2019:1314-1324. [19] Hu Jie, Shen Li, and Sun Gang. Squeeze-and-Excitation Networks[J]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE, 2018: 2011-2023. [20] Wang Qilong, Wu Banggu, Zhu Pengfei, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// Proceedings of 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE,2020:11531-11539. [21] Soares EA, Angelov PP, Biaso S, et al. SARS-CoV-2 CT-scan dataset: a large dataset of real patients CT scans for SARS-CoV-2 identification[EB/OL].https://eprints.lancs.ac.uk/id/eprint/143767/,2020-05-04/2022-11-03. [22] Yang Xingyi, He Xuehai, Zhao Jinyu,et al. COVID-CT-Dataset:a ct scan dataset about COVID-19[EB/OL]. https://arxiv.org/abs/2003.13865,2020-03-30/2022-11-03. [23] Gunraj H, Wang Linda, Wong A. COVIDNet-CT: A tailored deep convolutional neural network design for detection of COVId-19 cases from chest CT images[J]. Frontiers in Medicine, 2020, 7: 608525. [24] 徐永红,王金萍, 马佳越. 基于时序心脏模型样本均衡方法的心律失常分类[J].中国生物医学工程学报,2022,41(3):301-309. [25] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE,2016: 770-778. [26] Sandler M, Howard A, Zhu Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE,2018:4510-4520. [27] Chollet F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE,2017:1800-1807. [28] Szegedy C, Liu Wei, Jia Yangqing, et al. Going deeper with convolutions[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE,2015:1-9. [29] Chen Liang-Chieh, George P, Florian S, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL]. https://arxiv.org/abs/1706.05587,2017-06-17/2023-12-03. [30] Zhao Hengshuang, Shi Jianping, Qi Xiaojuan, et al. Pyramid scene parsing network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE,2017:2881-2890. [31] Raiko T, Valpola H, LeCun Y. Deep learning made easier by linear transformations in perceptions[J]. Computer Science, 2012: 924-932. [32] Vatanen T, Raiko T, Valpola H, et al. Pushing stochastic gradient towards second-order methods-backpropagation learning with transformations in nonlinearities[C]// Neural Information Processing: 20th International Conference (ICONIP 2013. Daegu: Springer,2013:442-449.
