多卷积神经网络的胸部X光片肺结核检测方法

doi:10.3778/j.issn.1002-8331.2304-0148

摘要/Abstract

摘要： 由于肺结核病灶区域与正常肺部区域之间的差异微小，导致肺结核疾病难以准确检测。针对此问题，提出了一种基于深度可分离卷积和图卷积相结合的肺结核疾病检测算法。使用深度可分离卷积模块提取图像的局部特征；使用图卷积模块提取图像的全局特征；通过一个捷径分支操作，将提取的局部特征和全局特征进行融合；将融合后的特征经过线性层输出检测的结果。算法模型在中国广东省深圳市第三医院收集的公开可用的正面胸部X光片数据集上进行了充分的实验与验证。实验结果表明，所提算法模型与基准模型相比，在Accuracy、Precision、Recall和F1-Score四个评价指标上分别提高了2.98、3.23、2.94和3.08个百分点，从而证明了所提方法的有效性。

关键词: X光片, 深度可分离卷积, 图卷积网络, 肺结核检测

Abstract: Due to the small difference between the focus area of pulmonary tuberculosis and the normal lung area, it is difficult to accurately detect the pulmonary tuberculosis disease. To solve this problems, a tuberculosis disease detection algorithm based on the combination of deep separable convolution and graph convolution is proposed. Firstly, the depth separable convolution module is used to extract the local features of the image. Secondly, the graph convolution module is used to obtain the global features of the image. Then, using a shortcut branching operation, the extracted local and global features are fused. Finally, the fused features are output through the linear layer to output the detection results. The algorithm model has been fully experimented and verified on the publicly available positive chest X-Ray dataset collected by the Third Hospital of Shenzhen City, Guangdong Province, China. Experimental results show that compared with the benchmark model, the proposed algorithm model improves by 2.98, 3.23, 2.94 and 3.08 percentage points on the four evaluation indicators of Accuracy, Precision, Recall and F1-Score, respectively, which proves the effectiveness of the proposed method.

Key words: X-Ray, depth separable convolution, graph convolutional network, tuberculosis detection

崔少国, 解筝, 宋豪杰. 多卷积神经网络的胸部X光片肺结核检测方法[J]. 计算机工程与应用, 2024, 60(13): 246-254.

CUI Shaoguo, XIE Zheng, SONG Haojie. Multi-Convolutional Neural Network for Detection of Pulmonary Tuberculosis on Chest X-Ray[J]. Computer Engineering and Applications, 2024, 60(13): 246-254.

参考文献

[1] PEPPERELL C S. Evolution of tuberculosis pathogenesis[J]. Annual Review of Microbiology, 2022, 76: 661-680.
[2] KOCH A, MIZRAHI V. Mycobacterium tuberculosis[J]. Trends in Microbiology, 2018, 26(6): 555-556.
[3] SIEGEL R L, MILLER K D, FUCHS H E, et al. Cancer statistics, 2022[J]. CA, 2022, 72(1): 7-33.
[4] 何玉麟, 许传军, 李宏军, 等. 肺结核影像诊断标准[J]. 临床放射学杂志, 2020, 39(11): 2142-2146.
HE Y L, XU C J, LI H J, et al. Imaging diagnostic criteria for pulmonary tuberculosis[J]. Journal of Clinical Radiology, 2020, 39(11): 2142-2146.
[5] 吴键, 侯代伦. 深度学习在肺结核影像诊断中的应用[J]. 中国防痨杂志, 2022, 44(1): 91-94.
WU J, HOU D L. Application of deep learning in pulmonary tuberculosis imaging diagnosis[J]. Chinese Journal of Antituberculosis, 2022, 44(1): 91-94.
[6] 赵晓平, 王荣发, 孙中波, 等. 改进DenseNet的乳腺癌病理图像八分类研究[J]. 计算机工程与应用, 2023, 59(5): 213-221.
ZHAO X P, WANG R F, SUN Z B, et al. Research on eight classifications of breast cancer pathological images based on improved dense net[J]. Computer Engineering and Applications, 2023, 59(5): 213-221.
[7] 吴辰文, 梁雨欣, 田鸿雁. 改进卷积神经网络的COVID-19 CT影像分类方法研究[J]. 计算机工程与应用, 2022, 58(2): 225-234.
WU C W, LIANG Y X, TIAN H Y. Research on COVID-19 CT image classification method based on improved convolutional neural network[J]. Computer Engineering and Applications, 2022, 58(2): 225-234.
[8] IQBAL A, USMAN M, AHMED Z. An efficient deep learning-based framework for tuberculosis detection using chest X-ray images[J]. Tuberculosis, 2022, 136: 102234.
[9] 凌语, 孙自强. 基于卷积神经网络的乳腺病理图像识别算法[J]. 江苏大学学报 (自然科学版), 2019, 40(5): 573-578.
LING Y, SUN Z Q. Recognition algorithm of breast pathological images based on convolutional neural network[J]. Journal of Jiangsu University (Natural Science Edition), 2019, 40(5): 573-578.
[10] RAHMAN M, CAO Y, SUN X, et al. Deep pre-trained networks as a feature extractor with XGBoost to detect tuberculosis from chest X-ray[J]. Computers & Electrical Engineering, 2021, 93: 107252.
[11] HERRERA D M, HAWORTH B M, KEYNAN Y. Review of evidence for using chest X-rays for active tuberculosis screening in long-term care in Canada[J]. Frontiers in Public Health, 2020, 8: 16.
[12] LI J, YIP B H K, LEUNG C, et al. Screening for latent and active tuberculosis infection in the elderly at admission to residential care homes: a cost-effectiveness analysis in an intermediate disease burden area[J]. Plos One, 2018, 13(1): 1-18.
[13] ALFADHLI F H O, MAND A A, SAYEED M S, et al. Classification of tuberculosis with SURF spatial pyramid features[C]//Proceedings of the 2017 International Conference on Robotics, Automation and Sciences (ICORAS), 2017: 1-5.
[14] SINGH N, HAMDE S. Tuberculosis detection using shape and texture features of chest X-rays[C]//Proceedings of the 7th ICIECE 2018. Singapore: Springer, 2019: 43-50.
[15] CHANDRA T B, VERMA K, SINGH B K, et al. Automatic detection of tuberculosis related abnormalities in Chest X-ray images using hierarchical feature extraction scheme[J]. Expert Systems with Applications, 2020, 158: 113514.
[16] LIU C, CAO Y, ALCANTARA M, et al. TX-CNN: detecting tuberculosis in chest X-ray images using convolutional neural network[C]//Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), 2017: 2314-2318.
[17] HOODA R, SOFAT S, KAUR S, et al. Deep-learning: a potential method for tuberculosis detection using chest radiography[C]//Proceedings of the 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2017: 497-502.
[18] DINESH J S R, RAJESH K B. Tuberculosis (TB) detection system using deep neural networks[J]. Neural Computing and Applications, 2019, 31: 1533-1545.
[19] SZEGEDY C, VANHOUCKE V, LOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2818-2826.
[20] 张冉. 注意力引导的深度学习算法在胸部X光肺结核检测中的应用研究[D]. 济南: 山东师范大学, 2020.
ZHANG R. Research on attention-guided deep learning algorithm in chest X-ray tuberculosis detection[D]. Jinan: Shandong Normal University, 2020.
[21] RAJPURKAR P, O’CONNELL C, SCHECHTER A, et al. CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest X-rays in patients with HIV[J]. NPJ Digital Medicine, 2020, 3(1): 115.
[22] ALAWI A E B, AL-BASSER A, SALLAM A, et al. Convolutional neural networks model for screening tuberculosis disease[C]//Proceedings of the 2021 International Conference of Technology, Science and Administration (ICTSA), 2021: 1-5.
[23] DEY S, ROYCHOUDHURY R, MALAKAR S, et al. An optimized fuzzy ensemble of convolutional neural networks for detecting tuberculosis from Chest X-ray images[J]. Applied Soft Computing, 2022, 114: 108094.
[24] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1251-1258.
[25] ZHANG X Y, ZHOU X Y, LIN M X, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 6848-6856.
[26] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[27] SANDLER M, HOWARD A, ZHU M, et al. MobileNetv2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[28] 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, 2016: 770-778.
[29] HAN K, WANG Y, GUO J, et al. Vision GNN: an image is worth graph of nodes[C]//Advances in Neural Information Processing Systems, 2022: 8291-8303.
[30] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv:2010.11929, 2020.
[31] LIU Z, MAO H, WU C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 11976 -11986.
[32] HOWARD A, SANDLER M, CHU G, et al. Searching for MobileNetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 1314-1324.