Detection method of pulmonary nodules based on improved residual structure

doi:10.11772/j.issn.1001-9081.2019122095

Abstract

Abstract: In order to solve the problems of high computing cost and over-fitting of the model caused by complicated network structure in pulmonary nodule detection method, an improved residual network structure combining deep separable convolution and pre-activation was proposed. And the proposed network structure was applied to a pulmonary nodule detection model. Based on the target detection network Faster R-CNN, with U-Net coder-decoder structure adopted, the deep separable convolution and pre-activation operations were used by the model to improve the 3D residual network structure. Firstly, with the use of deep separable convolution, the complexity and computing cost of the model were reduced. Then, the regularization of the model was improved by introducing the pre-activation operation, and the phenomenon of overfitting was alleviated. Finally, the rectangular convolution kernel was used to expand the receptive field of the convolution operation on the premise that the computing cost of the model was slightly increased, so as to effectively take into account both the global and local characteristics of the pulmonary nodules. On the LUNA16 dataset, the proposed method has the sensitivity of 96.04%, and the Free-response area under the Receiver Operating Characteristic curve (FROC) score of 83.23%. The experimental results show that the method improves the sensitivity of pulmonary nodule detection, effectively reduces the average number of false positives in the detection results, and improves the detection efficiency. This proposed method can effectively assist radiologists in detecting pulmonary nodules.

Key words: pulmonary nodule detection, U-Net, Faster R-CNN, deep separable convolution, pre-activation

摘要： 针对肺结节检测方法中网络结构复杂所导致的模型计算量大、过拟合的问题，提出了一种结合深度可分离卷积和预激活的改进残差网络结构，将提出的网络结构应用于肺结节检测模型。该模型以目标检测网络Faster R-CNN为基础，采用U-Net编码解码器结构，利用深度可分离卷积和预激活操作改进了三维残差网络结构。首先，通过使用深度可分离卷积，模型复杂度和计算量大幅度降低；其次，通过使用预激活，模型的正则化得到改善，缓解了过拟合现象；最后，采用矩形卷积核在少量增加模型计算量的前提下扩大了卷积操作的感受野，有效地兼顾了肺结节的全局和局部特征。在LUNA16数据集上的检测中所提方法的灵敏度为96.04%，无限制接收者操作特征曲线下面积（FROC）得分为83.23%。实验结果表明：该方法提高了肺结节检测的灵敏度，又有效降低了检测结果的平均假阳性个数，同时提高了检测效率，可有效辅助放射科医师对肺结节进行检测。

关键词: 肺结节检测, U-Net, Faster R-CNN, 深度可分离卷积, 预激活

CLC Number:

TP391.7

SHI Lukui, MA Hongqi, ZHANG Chaozong, FAN Shiyan. Detection method of pulmonary nodules based on improved residual structure[J]. Journal of Computer Applications, 2020, 40(7): 2110-2116.

石陆魁, 马红祺, 张朝宗, 樊世燕. 基于改进残差结构的肺结节检测方法[J]. 计算机应用, 2020, 40(7): 2110-2116.

References

[1] 张鹏, 徐欣楠, 王洪伟, 等. 基于深度学习的计算机辅助肺癌诊断方法[J]. 计算机辅助设计与图形学学报,2018,30(1):90-99.(ZHANG P,XU X N,WANG H W,et al. Computer-aided lung cancer diagnosis approaches based on deep learning[J]. Journal of Computer-Aided Design and Computer Graphics,2018,30(1):90-99.)
[2] WU S, WANG J. Pulmonary nodules 3D detection on serial CT scans[C]//Proceedings of the 3rd Global Congress on Intelligent Systems. Piscataway:IEEE, 2012:257-260.
[3] KO J P,NAIDICH D P. Computer-aided diagnosis and the evaluation of lung disease[J]. Journal of Thoracic Imaging,2004,19(3):136-155.
[4] DEHMESHKI J,AMIN H,VALDIVIESO M,et al. Segmentation of pulmonary nodules in thoracic CT scans:a region growing approach[J]. IEEE Transactions on Medical Imaging,2008,27(4):467-480.
[5] LASSEN B C, JACOBS C, KUHNIGK J M, et al. Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans[J]. Physics in Medicine and Biology,2015,60(3):1307-1323.
[6] BAE K T,KIM J S,NA Y H,et al. Pulmonary nodules:automated detection on CT images with morphologic matching algorithm-preliminary results[J]. Radiology, 2005, 236(1):286-293.
[7] OKUMURA T,MIWA T,KAKO J I,et al. Automatic detection of lung cancers in chest CT images by variable N-Quoit filter[C]//Proceedings of the 14th International Conference on Pattern Recognition. Piscataway:IEEE, 1998:1671-1673.
[8] SIVAKUMAR S,CHANDRASEKAR C. Lung nodule detection using fuzzy clustering and support vector machines[J]. International Journal of Engineering and Technology, 2013, 5(1):179-185.
[9] SANTOS A M, DE CARVALHO FILHO A O, SILVA A C, et al. Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models,Tsallis entropy and SVM[J]. Engineering Applications of Artificial Intelligence, 2014, 36(C):27-39.
[10] MURPHY K,VAN GINNEKEN B,SCHILHAN A M R,et al. A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbor classification[J]. Medical Image Analysis, 2009, 13(5):757-770.
[11] 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.
[12] SHEN W,ZHOU M,YANG F,et al. Multi-scale convolutional neural networks for lung nodule classification[C]//Proceedings of the 24th International Conference on Information Processing in Medical Imaging, LNCS 9123. Cham:Springer, 2015:588-599.
[13] 赵鹏飞, 赵涓涓, 强彦, 等. 多输入卷积神经网络肺结节检测方法研究[J]. 计算机科学,2018,45(1):162-166.(ZHAO P F, ZHAO J J,QIANG Y,et al. Study on detection method of pulmonary nodules with multiple input convolution neural network[J]. Computer Science, 2018, 45(1):162-166.)
[14] ALAKWAA W,NASSEF M,BADR A. Lung cancer detection and classification with 3D Convolutional Neural Network (3D-CNN)[J]. International Journal of Advanced Computer Science and Applications, 2017, 8(8):409-417.
[15] DOU Q,CHEN H,JIN Y,et al. Automated pulmonary nodule detection via 3D ConvNets with online sample filtering and hybrid-loss residual learning[C]//Proceedings of the 20th International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10435. Cham:Springer, 2017:630-638.
[16] 杨晶晶, 王骞, 宣晓华. 基于深度卷积神经网络算法的肺结节检测模型[J]. 数学建模及其应用,2017,6(4):1-9.(YANG J J,WANG Q,XUAN X H. Computer-aided diagnosis for detecting lung nodules by convolutional neural networks[J]. Mathematical Modeling and Application, 2017, 6(4):1-9.)
[17] 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.
[18] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Interventions,LNCS 9351. Cham:Springer, 2015:234-241.
[19] CHOLLET F. Xception:deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:1800-1807.
[20] 金弘晟. 肺部CT图像中肺结节自动检测算法的研究与实现[D]. 杭州:浙江大学, 2018:8-13.(JIN H S. Research and implementation of automatic pulmonary nodule detection algorithm in pulmonary CT images[D]. Hangzhou:Zhejiang University,2018:8-13.)
[21] MESSAY T,HARDIE R C,TUINSTRA T R. Segmentation of pulmonary nodules in computed tomography using a regression neural network approach and its application to the lung image database consortium and image database resource initiative dataset[J]. Medical Image Analysis, 2015, 22(1):48-62.
[22] SA R,OWENS W,WIEGAND R,et al. Intervertebral disc detection in X-ray images using Faster R-CNN[C]//Proceedings of the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway:IEEE, 2017:564-567.
[23] 吴晓凤, 张江鑫, 徐欣晨. 基于Faster R-CNN的手势识别算法[J]. 计算机辅助设计与图形学学报,2018,30(3):468-476. (WU X F,ZHANG J X,XU X C. Hand gesture recognition algorithm based on faster R-CNN[J]. Journal of Computer-Aided Design and Computer Graphics, 2018, 30(3):468-476.)
[24] HE K M,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.
[25] 张婷. 基于受限玻尔兹曼机的肺结节检测与诊断模型[D]. 太原:太原理工大学,2018:41-42.(ZHANG T. Research on detection and diagnosis methods for pulmonary nodules based on restricted Boltzmann machine[D]. Taiyuan:Taiyuan University of Technology, 2018:41-42.)
[26] 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.
[27] Ping An Technology(Shenzhen)Co., Ltd. 3DCNN for lung nodule detection and false positive reduction[EB/OL].[2019-09-10]. https://grand-challenge-public.s3.amazonaws.com/f/challenge/71/8ac994bc-9951-420d-a7e5-21050c5b4132/20180102_081812_PAtech_NDET.pdf.