基于深度混合卷积模型的肺结节检测方法

doi:10.11772/j.issn.1001-9081.2020020192

计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2904-2909.DOI: 10.11772/j.issn.1001-9081.2020020192

基于深度混合卷积模型的肺结节检测方法

戚永军^1,2,3, 顾军华^1,2,4,5, 张亚娟^4,5, 王锋⁴, 田泽培⁴

1. 省部共建电工装备可靠性与智能化国家重点实验室(河北工业大学), 天津 300132;
2. 河北省电磁场与电器可靠性重点实验室(河北工业大学), 天津 300132;
3. 北华航天工业学院信息技术中心, 河北廊坊 065000;
4. 河北工业大学人工智能与数据科学学院, 天津 300401;
5. 河北省大数据计算重点实验室(河北工业大学), 天津 300401

收稿日期:2020-02-26 修回日期:2020-05-22 出版日期:2020-10-10 发布日期:2020-05-27
通讯作者: 顾军华
作者简介:戚永军(1976-),男,河北唐山人,高级工程师,博士研究生,主要研究方向:计算机视觉、深度学习;顾军华(1966-),男,河北赵县人,教授,博士,CCF会员,主要研究方向:智能信息处理、数据挖掘;张亚娟(1984-),女,河北廊坊人,高级实验师,硕士,主要研究方向:数据挖掘、图像处理;王锋(1995-),男,河北保定人,硕士研究生,主要研究方向:医学图像处理、图像检索;田泽培(1994-),女,河北石家庄人,硕士研究生,主要研究方向:医学图像处理、目标检测。
基金资助:
国家自然科学基金资助项目（61702157）；河北省创新能力提升计划项目（199676146H）；北华航天工业学院青年基金资助项目（KY202022）。

Deep mixed convolution model for pulmonary nodule detection

QI Yongjun^1,2,3, GU Junhua^1,2,4,5, ZHANG Yajuan^4,5, WANG Feng⁴, TIAN Zepei⁴

1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment;(Hebei University of Technology), Tianjin 300132, China;
2. Hebei Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability;(Hebei University of Technology), Tianjin 300132, China;
3. Information Technology Center, North China Institute of Aerospace Engineering, Langfang Hebei 065000, China;
4. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China;
5. Hebei Key Laboratory of Big Data Calculation(Hebei University of Technology), Tianjin 300401, China

Received:2020-02-26 Revised:2020-05-22 Online:2020-10-10 Published:2020-05-27
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61702157), the Innovation Capacity Improvement Program of Hebei Province (199676146H), the Youth Foundation of North China Institute of Aerospace Engineering (KY202022).

摘要/Abstract

摘要： 基于高维肺部计算机断层扫描（CT）图像的肺结节检测是一项极具挑战性的任务。在诸多肺结节检测算法中，深度卷积神经网络（CNN）最引人注目，其中二维（2D） CNN具有预训练模型多、检测效率高等优点，应用非常广泛，但肺结节本质是三维（3D）病灶，2D CNN会不可避免地造成信息损失，从而影响检测精度。3D CNN能充分利用CT图像空间信息，有效提升检测精度，但是3D CNN存在参数多、计算消耗大、过拟合风险高等不足。为了兼顾两者的优势，提出基于深度混合CNN的肺结节检测模型，通过在神经网络模型的浅层部署3D CNN，在模型的深层部署2D CNN，并增加反卷积模块，融合了多层级的图像特征，达到了在不损失检测精度的情况下减少模型参数、增强模型泛化能力，提高检测效率的目的。在LUNA16数据集上的实验结果表明，所提出的模型在平均每次扫描8个假阳性的情况下的敏感度为0.924，优于现有的先进模型。

关键词: 深度学习, 特征融合, 肺结节检测, 计算机辅助诊断, CT图像

Abstract: Pulmonary nodule detection is a very challenging task based on high-dimensional lung Computed Tomography (CT) images. Among many pulmonary nodule detection algorithms, the deep Convolutional Neural Network (CNN) is the most attractive one. In this kind of networks, the Two-Dimensional (2D) CNNs with many pre-trained models and high detection efficiency are widely used. However, the nature of pulmonary nodules is the Three-Dimensional (3D) lesion, so that the 2D CNNs will inevitably cause information loss and thereby affect the detection accuracy. The 3D CNNs can make full use of the spatial information of CT images and effectively improve the detection accuracy, but the 3D CNNs have shortcomings such as many parameters, large calculation consumption and high risk of over fitting. In order to take the advantages of the two networks, a pulmonary nodule detection model based on a deep mixed CNN was proposed. By deploying 3D CNN in the shallow layer of the neural network model and 2D CNN in the deep layer of the model, and adding a deconvolution module to fuse multi-layer image features together, the model parameters were reduced and the generalization ability and the detection efficiency of the model were improved without decreasing the detection accuracy. Experimental results on LUNA16 dataset show that the proposed model has the sensitivity reached 0.924 under the condition of average 8 false positives per scan, which outperforms the existing state-of-the-art models.

Key words: deep learning, feature fusion, pulmonary nodule detection, Computer Aided Diagnosis (CAD), Computed Tomography (CT) image

中图分类号:

TP391

戚永军, 顾军华, 张亚娟, 王锋, 田泽培. 基于深度混合卷积模型的肺结节检测方法[J]. 计算机应用, 2020, 40(10): 2904-2909.

QI Yongjun, GU Junhua, ZHANG Yajuan, WANG Feng, TIAN Zepei. Deep mixed convolution model for pulmonary nodule detection[J]. Journal of Computer Applications, 2020, 40(10): 2904-2909.

参考文献

[1] FILHO A O D C,SILVA A C,DE PAIVA A C,et al. 3D shape analysis to reduce false positives for lung nodule detection systems[J]. Medical and Biological Engineering and Computing,2017,55(8):1199-1213.
[2] MONKAM P,QI S,MA H,et al. Detection and classification of pulmonary nodules using convolutional neural networks:a survey[J]. IEEE Access,2019,7:78075-78091.
[3] SETIO A A A,TRAVERSO A,DE BEL T,et al. Validation, comparison,and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images:the LUNA16 challenge[J]. Medical Image Analysis,2017,42:1-13.
[4] LIU X,HOU F,QIN H,et al. Multi-view multi-scale CNNs for lung nodule type classification from CT images[J]. Pattern Recognition,2018,77:262-275.
[5] SETIO A 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.
[6] VAN GINNEKEN B,SETIO A A A,JACOBS C,et al. Off-theshelf convolutional neural network features for pulmonary nodule detection in computed tomography scans[C]//Proceedings of the IEEE 12th International Symposium on Biomedical Imaging. Piscataway:IEEE,2015:286-289.
[7] ZHU W,VANG Y S,HUANG Y,et al. DeepEM:deep 3D ConvNets with EM for weakly supervised pulmonary nodule detection[C]//Proceedings of the 2018 Medical Image Computing and Computer-Assisted Intervention, LNCS 11071. Cham:Springer,2018:812-820.
[8] DOU Q,CHEN H,YU L,et al. Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection[J]. IEEE Transactions on Biomedical Engineering,2017,64(7):1558-1567.
[9] SUN N,YANG D,FANG S,et al. Deep convolutional nets for pulmonary nodule detection and classification[C]//Proceedings of the 2018 International Conference on Knowledge Science, Engineering and Management,LNCS 11062. Cham:Springer, 2018:197-208.
[10] TAO Q,GE Z,CAI J,et al. Improving deep lesion detection using 3D contextual and spatial attention[C]//Proceedings of the 2019 International Conference on Medical Image Computing and Computer-Assisted Intervention,LNCS 11769. Cham:Springer, 2019:185-193.
[11] ZHANG C,BENGIO S,HARDT M,et al. Understanding deep learning requires rethinking generalization[EB/OL].[2020-01-20]. https://arxiv.org/pdf/1611.03530.pdf.
[12] JAVAID M,JAVID M,ZIA UR REHMAN M,et al. A novel approach to CAD system for the detection of lung nodules in CT images[J]. Computer Methods and Programs in Biomedicine, 2016,135:125-139.
[13] LI Q,SONE S,DOI K. Selective enhancement filters for nodules, vessels,and airway walls in two- and three-dimensional CT scans[J]. Medical Physics,2003,30(8):2040-2051.
[14] GURCAN M N,SAHINER B,PETRICK N,et al. Lung nodule detection on thoracic computed tomography images:preliminary evaluation of a computer-aided diagnosis system[J]. Medical Physics,2002,29(11):2552-2558.
[15] BAR Y,DIAMANT I,WOLF L,et al. Chest pathology detection using deep learning with non-medical training[C]//Proceedings of the IEEE 12th International Symposium on Biomedical Imaging. Piscataway:IEEE,2015:294-297.
[16] YPSILANTIS P P, MONTANA G. Recurrent convolutional networks for pulmonary nodule detection in CT imaging[EB/OL].[2019-12-21]. https://arxiv.org/pdf/1609.09143.pdf.
[17] ROTH H R,LU L,LIU J,et al. Improving computer-aided detection using convolutional neural networks and random view aggregation[J]. IEEE Transactions on Medical Imaging,2016,35(5):1170-1181.
[18] 吕晓琪, 吴凉, 谷宇, 等. 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):1211-1218.(LYU X Q,WU L,GU Y,et al. Detection of low dose CT pulmonary nodules based on 3D convolution neural network[J]. Optics and Precision Engineering,2018,26(5):1211-1218.)
[19] ZHU W,LIU C,FAN W,et al. DeepLung:deep 3D dual path nets for automated pulmonary nodule detection and classification[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE, 2018:673-681.
[20] GLOROT X,BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[J]. Proceedings of Machine Learning Research,2010,9:249-256.
[21] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[22] REN S,HE K,GIRSHICK R,et al. Faster R-CNN:towards realtime object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(6):1137-1149.
[23] LIAO F,LIANG M,LI Z,et al. Evaluate the malignancy of pulmonary nodules using the 3-D deep leaky noisy-or network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(11):3484-3495.

基于深度混合卷积模型的肺结节检测方法

Deep mixed convolution model for pulmonary nodule detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[3]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[4]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[5]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[6]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[7]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[8]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[9]	王伟, 赵尔平, 崔志远, 孙浩. 基于HowNet义原和Word2vec词向量表示的多特征融合消歧方法[J]. 计算机应用, 2021, 41(8): 2193-2198.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[13]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[14]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[15]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.