基于三维卷积神经网络的低剂量CT肺结节检测

为提高早期肺癌筛查过程中肺结节的检出率, 提出利用三维卷积神经网络进行低剂量CT肺结节检测。首先采用多方向形态学滤波算法对低剂量序列CT图像进行预处理; 接着, 利用改进三维区域生长与凸包算法相结合进行肺实质分割; 然后提取三维候选结节, 为了解决卷积神经网络对样本不平衡的敏感问题, 对三维候选结节正样本进行旋转和光照处理; 最后在不同的网络参数下, 对ELCAP数据库中50个序列低剂量肺癌筛查数据进行4组实验。实验结果表明, 通过对网络参数的不断优化, 准确度、灵敏度、特异度以及ROC曲线的AUC值分别达到了84.6%、88.89%、8032%及0.924 4。该方法能够正确地对低剂量CT肺结节进行检测, 与文献所提出肺结节检测算法相比, 准确度、灵敏度和特异度分别平均提高了5.37%、5.6%和10.42%, 综合性能较强, 可以为肺癌筛查提供有效的帮助。

Abstract

To improve the detection rate of pulmonary nodules in early lung cancer screening, a low-dose CT pulmonary nodule detection algorithm based on 3D convolution neural network was presented. First, the multi-directional morphological filtering algorithm was used to preprocess low-dose sequence CT image. The improved 3D region growth algorithm combined with the convex hull algorithm was used for lung parenchymal segmentation. Then the 3D candidate nodules were routed and illuminated in order to solve the convolution neural network on the sample imbalance sensitive issues. Finally, in situations of different network parameters, four groups of experiments were performed on the 50 sequences of low-dose lung cancer screening data in ELCAP database. The results showed that accuracy, sensitivity, specificity and ROC curve of the AUC values were 84.6%, 88.89%, 80.32% and 0.924 4 respectively by the constant optimization of network parameters. The proposed algorithm can correctly detect low-dose lung nodules, with the the accuracy, sensitivity, and specificity increased by 5.37%, 5.6% and 10.42%, respectively, which is more comprehensive and can provide effective help for lung cancer screening compared with conventional lung nodule detection algorithm.

参考文献

[1] YPSILANTISP P, MONTANA G. Recurrent convolutional networks for pulmonary nodule detection in CT imaging ［J］. arXiv: 1609.09143, 2016.

[2] National Lung Screening Trial Research Team, ABERLE D R, ADAMS A M, et al.. Reduced lung-cancer mortality with low-dose computed tomographic screening ［J］. The New England Journal of Medicine, 2011, 365(5): 395-409.

[3] DECARVALHO FILHO A O, SILVA A C, DE PAIVA A C, et al.. 3D shape analysis to reduce false positives for lung nodule detection systems ［J］. Medical & Biological Engineering & Computing, 2017, 55(8): 1199-1213.

[4] 杨佳玲, 赵涓涓, 强彦, 等. 基于深度信念网络的肺结节良恶性分类［J］. 科学技术与工程, 2016, 16(32): 69-74.

YANGJ L, ZHAO J J, QIANG Y, et al.. A classification method of pulmonary nodules based on deep belief network ［J］. Science Technology and Engineering, 2016, 16(32): 69-74. (in Chinese)

[5] 刘智, 黄江涛, 冯欣. 构建多尺度深度卷积神经网络行为识别模型［J］. 光学精密工程, 2017, 25(3): 799-805.

LIU ZH, HUANG J T, FENG X. Action recognition model construction based on multi-scale deep convolution neural network ［J］. Opt. Precision Eng., 2017, 25(3): 799-805. (in Chinese)

[6] SETIOA A A, CIOMPI F, LITJENS G, et al.. Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks ［J］. IEEE Transactions on Medical Imaging, 2016, 35(5): 1160-1169.

[7] DA SILVAG L F, SILVA A C, DE PAIVA A C, et al.. Classification of malignancy of lung nodules in CT images using convolutional neural network ［J］. Workshop de Informática Médica, 2016, 16: 2481-2489.

[8] 张云逸. 低剂量CT图像的质量改善算法研究［D］. 郑州: 郑州大学, 2015.

ZHANG Y Y. Study of image quality improvement algorithm for low-dose CT ［D］. Zhengzhou: Zhengzhou University, 2015. (in Chinese)

[9] 杜兰, 刘彬, 王燕, 等. 基于卷积神经网络的SAR图像目标检测算法［J］. 电子与信息学报, 2016, 38(12): 3018-3025.

DUL, LIU B, WANG Y, et al.. Target detection method based on convolutional neural network for SAR image ［J］. Journal of Electronics & Information Technology, 2016, 38(12): 3018-3025. (in Chinese)

[10] 熊昌镇, 单艳梅, 郭芬红. 结合主体检测的图像检索方法［J］. 光学精密工程, 2017, 25(3): 792-798.

XIONG CH ZH, SHAN Y M, GUO F H. Image retrieval method based on image principal part detection ［J］. Opt. Precision Eng., 2017, 25(3): 792-798. (in Chinese)

[11] ELCAP Public Lung Image Database ［DB/OL］. http: //www.via.cornell.edu/databases/lungdb.html.

[12] 李勇, 苗壮, 王青竹. 纹理引导的稀疏张量表示及在肺CT图像中的应用［J］. 光学精密工程, 2015, 23(2): 550-556.

LI Y, MIAO ZH, WANG Q ZH. Texture-guided sparse tensor representation and its application in lung CT images ［J］. Opt. Precision Eng., 2015, 23(2): 550-556. (in Chinese)

[13] GLOROTX, BORDES A, BENGIO Y. Deep sparse rectifier neural networks ［C］. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, PMLR, 2012.

[14] YANG H, YU H Y, WANG G. Deep learning for the classification of lung nodules ［J］. arXiv: 1611.06651, 2016.

[15] DONG Y D, GUO H P, ZHI W M, et al.. Class imbalance oriented logistic regression ［C］. Proceedings of 2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, IEEE, 2014: 187-192.

[16] 刘露, 刘宛予, 楚春雨, 等. 胸部CT图像中孤立性肺结节良恶性快速分类［J］. 光学精密工程, 2009, 17(8): 2060-2068.

LIU L, LIU W Y, CHU CH Y, et al.. Fast classification of benign and malignant solitary pulmonary nodules in CT image ［J］. Opt. Precision Eng., 2009, 17(8): 2060-2068. (in Chinese)

[17] OROZCO H M, VILLEGAS O O V, SNCHEZ V G C, et al.. Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine ［J］. Biomedical Engineering Online, 2015, 14: 9.

[18] FARAGA A, ELHABIAN S Y, ELSHAZLY S A, et al.. Quantification of nodule detection in chest CT: a clinical investigation based on the ELCAP study ［C］. Proceedings of the 2nd International Workshop on Pulmonary Image Proceedings in Conjunction with MICCAI 2009, MICCAI, 2009.

[19] KUMAR D, WONG A, CLAUSID A. Lung nodule classification using deep features in CT images ［C］. Proceedings of the 12th Conference on Computer and Robot Vision, IEEE, 2015: 133-138.

[20] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络［J］. 自动化学报, 2016, 42(9): 1300-1312.

CHANG L. DENG X M, ZHOUM Q, et al.. Convolutional neural networks in image understanding ［J］. Acta Automatica Sinica, 2016, 42(9): 1300-1312. (in Chinese)

吕晓琪, 吴凉, 谷宇, 张文莉, 李菁. 基于三维卷积神经网络的低剂量CT肺结节检测[J]. 光学精密工程, 2018, 26(5): 1211. L Xiao-qi, WU Liang, GU Yu, ZHANG Wen-li, LI Jing. Detection of low dose CT pulmonary nodules based on 3D convolution neural network[J]. Optics and Precision Engineering, 2018, 26(5): 1211.

基于三维卷积神经网络的低剂量CT肺结节检测

关于本站 Cookie 的使用提示

全站搜索

基于三维卷积神经网络的低剂量CT肺结节检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索