|
|
|
| Benign and Malignant Diagnosis of Pulmonary Nodules Based on SE-CapsNet |
| Ye Feng1*, Wang Luyao1, Hong Wei2, Ding Guojun3, Che Jiarong1 |
1(School of Management, Zhejiang University of Technology, Hangzhou 310023, China)
2(Department of Thoracic Oncology, Zhejiang Cancer Hospital, Hangzhou 310023, China)
3(Department of Radiology, Zhejiang Cancer Hospital, Hangzhou 310023, China) |
|
|
|
|
Abstract Over the past few years, lung cancer has been the leading cause of cancer-related deaths. This paper proposed a SE-CapsNet classification method for the low-dose computed tomography (CT) image refinement preprocessing conditions. Our work solved the problems of low classification accuracy and high false positives in traditional lung nodule diagnosis methods, which improved the capsule neural network classification algorithm, including improving the latest Hinton's capsule neural network, introducing new non-linear activation vectors, avoiding global vector compression, and optimizing the model at the feature channel level by feature reweight. We used the automatic threshold method to process the CT images by calibrating the region of interest, and took the samples at the central nodule to obtain data samples of the pre-processing results. The public data set LIDC-IDRI containing 1010 cases and 30 cases of desensitized tumor patients eliminated sensitive information from hospital were used to evaluate the improved SE-CapsNet algorithm. The evaluation criteria mainly included accuracy, sensitivity and specificity. In the LIDC-IDRI dataset and the hospital dataset, the average accuracy of the SE-CapsNet algorithm reached 95.83% and 94.67%, respectively, which was superior to that by CapsNet classification algorithm. In addition, the classification algorithm also had obvious advantages in terms of time consumption, and the improved capsule network converged faster to obtain stable results.
|
|
Received: 06 March 2020
|
|
|
|
Corresponding Authors:
*E-mail: yefeng@zjut.edu.cn
|
|
|
|
[1] Zhou Maigeng,Wang Haidong, Zeng Xinying, et al. Mortality, morbidity, and risk factors in China and its provinces, 1990-2017: A systematic analysis for the Global Burden of Disease Study 2017[J]. The Lancet, 2019,394(10204): 1145-1158.
[2] Sverzellati N, Silva M, Calareso G, et al. Low-dose computed tomography for lung cancer screening: comparison of performance between annual and biennial screen[J]. Eur Radiol, 2016,26(11): 3821-3829.
[3] Leader JK,Warfel TE,Fuhrman CR, et al. Pulmonary nodule detection with low-dose CT of the lung:Agreement among radiologists[J]. AJR Am J Roentgenol, 2005,185(4): 973-978.
[4] Kalender WA. X-ray computed tomography[J]. Physics in Medicine & Biology, 2006,51(13):R29-R43.
[5] Kuruvilla J, Gunavathi K. Lung cancer classification using neural networks for CT images[J]. Comput Methods Programs Biomed, 2014,113(1): 202-209.
[6] Wang Wei, Ooi Beng Chin,Yang Xiaoyan,et al. Effective Multi-Modal Retrieval based on Stacked Auto-Encoders[J]. Proceedings of the VLDB Endowment, 2014,7(8):649-660.
[7] Cho KH, Raiko T, Ilin A, et al.A two-stage pretraining algorithm for deep Boltzmann machines[C]//Proceedings of 23rd International Conference on Artificial Neural Networks. Sofia: Springer Verlag,2013:106-113.
[8] 王伟胜, 骆嘉伟, 林红利. 医学图像计算机辅助诊断数据平台研究[J]. 中国生物医学工程学报, 2013,32(1): 105-108.
[9] He K, Zhang Xiangyu, Ren Shaoqing,et al. Deep Residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2016:770-778.
[10] Zhang Baihua,Qi Shouliang,Monkam P, et al. Ensemble learners of multiple deep cnns for pulmonary nodules classification using ct images[J]. IEEE Access, 2019,7(2019): 110358-110371.
[11] Song Qingzeng,Zhao Lei, Luo Xingke,et al. Using deep learning for classification of lung nodules on computed tomography images[J]. Journal of Healthcare Engineering, 2017,2017(1): 1-7.
[12] Yang He, Yu Hengyong.Deep learning for the classification of lung nodules[EB/OL].https://arxiv.org/abs/1611.06651,2016-11-26/2020-03-10.
[13] Ramaswamy S, Truong K. Pulmonary nodule classification with convolutional neural networks[EB/OL]. http://cs231n.stanford.edu/reports/2016/pdfs/324_Report.pdf,2016-10-06/2020-03-10.
[14] Zhao Xinzhuo, Liu Liyao, Qi Shouliang,et al. Agile convolutional neural network for pulmonary nodule classification using CT images[J]. International Journal of Computer Assisted Radiology and Surgery, 2018,13(4): 585-595.
[15] Hua KL,Hsu CH,Hidayati SC,et al. Computer-aided classification of lung nodules on computed tomography images via deep learning technique[J]. Onco Targets Ther, 2015,8:2015-2022.
[16] Fukushima K.1980-Fukushima-Neocognitron A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics,1980,36(4):193-202.
[17] Mukhometzianov R, Carrillo J.CapsNet comparative performance evaluation for image classification[EB/OL].https://arxiv.org/ftp/arxiv/papers/1805/1805.11195.pdf,2018-05-28/2020-03-10.
[18] Sabour S, Frosst N, Hinton GE, et al. Dynamic routing between capsules[C]//Advances in Neural Information Processing Systems. San Diego: Neural Information Processing Systems Foundation, 2017:3859-3869.
[19] Wei Ying,Shen Guo,Li Juan-juan.A Fully Automatic Method for Lung ParenchymaSegmentation and Repairing[J]. J Digit Imaging, 2013,26(3): 483-495.
[20] Hu Shiying,Hoffman E A,Reinhardt J M,et al.Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images[J]. IEEE Trans on Medical Imaging,2001, 20(6):490-498.
[21] Fangfang Han, Guopeng Zhang, Huafeng Wang,et al, A texture feature analysis for diagnosis of pulmonary nodules using lidc-idri database[C]//IEEE International Conference on Medical Imaging Physics and Engineering.Shenyang:IEEE, 2013:14-18.
[22] Fangfang Han, Huangferng Wang, Guopeng Zhang,et al. Texture feature analysis for computer-aided diagnosis on pulmonary nodules[J]. Journal of Digit Imaging,2015,28(1):99-115.
[23] Hu Jie,Shen Li,Albanie S.Squeeze-and-Excitation Networks[EB/OL].https://arxiv.org/abs/1709.01507,2017-09-15/2020-03-10.
[24] 陶卿,姚穗,范劲松,等.一种新的机器学习算法:Support Vector Machine [J].模式识别与人工智能,2000,13(3):285-290.
[25] Armato S G, McLennan G, Bidaut L, et al.The lung image database consortium (LIDC) and image database resource initiative (IDRI): A completed reference database of lung nodules on CT scans[J]. Medical Physics,2011,38(2):915-931.
[26] Shen Wei,Zhou Mu,Yang Feng,et al.Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification[J]. Pattern Recognition, 2017, 61:663-673.
[27] Henry K, Benjamin G, Gu Yuhua, et al. Effect of texture features in computer aided diagnosis of pulmonary nodules in low-dose computed tomography[C]// 2013 IEEE International Conference on Systems, Man, and Cybernetics. Manchester:IEEE,2013.:3887-3891.
[28] Kumar, D, Wong A, David C. Lung nodule classification using deep features in CT images[C]//2015 12th Conference on Computer and Robot Vision. Halifax:IEEE,2015:133-138.
[29] Dey R,Lu Zhongjie,Hong Yi. Diagnostic classification of lung nodules using 3D neural networks[C]//The 15th International Symposium on Biomedical Imaging. Washington DC: IEEE, 2018: 774-778.
[30] Liu Shuang,Xie Yiting,Jirapatnakul A, et al. Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks[J].J Med Imaging (Bellingham), 2017,4(4): 041308.
[31] Dou Qi,Chen Hao,Yu Lequan, et al.Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection[J]. IEEE Trans Biomed Eng, 2017,64(7):1558-1567. |
|
|
|
