基于多尺度特征结构的U-Net肺结节检测算法

doi:10.19678/j.issn.1000-3428.0051769

摘要/Abstract

摘要：

针对肺结节低层特征在网络传输过程中的缺失问题，基于多尺度特征结构，提出一种改进的U-Net卷积神经网络肺结节检测算法。采用卷积操作与池化操作获取高层特征，通过密集网络使得特征信息在输入层和输出层之间高速流通，并结合扩张卷积生成多尺度特征，提高肺结节低层特征的利用率。实验结果表明，与传统U-Net卷积神经网络的肺结节检测算法相比，改进算法对于小型结节的检测准确率约提高20%，可实现更准确的肺部病灶区域定位。

关键词: 小目标检测, 卷积神经网络, 深度学习, 密集网络, 肺结节

Abstract:

Aiming at the defect problem in the low-level characteristics of pulmonary nodules in the process of network transmission,an improved U-Net convolution neural network algorithm based on multi-scale feature structure for pulmonary nodule detection is proposed.High-level features are acquired by convolution and pooling operations,high-speed flow of feature information between input and output layers is achieved by using dense network,and multi-scale features are generated combining with expanded convolution to improve the utilization of low-level features of pulmonary nodules.Experimental results show that,compared with the traditional U-Net convolution neural network detection algorithm of pulmonary nodules,the improved algorithm improves the detection accuracy of small nodules by nearly 20%,and achieves more accurate localization of pulmonary lesions.

Key words: small object detection, Convolutional Neural Network(CNN), deep learning, dense network, pulmonary nodule

中图分类号:

TP391.41

朱辉,秦品乐. 基于多尺度特征结构的U-Net肺结节检测算法[J]. 计算机工程, 2019, 45(4): 254-261.

ZHU Hui,QIN Pinle. U-Net Pulmonary Nodule Detection Algorithm Based on Multi-scale Feature Structure[J]. Computer Engineering, 2019, 45(4): 254-261.

https://www.ecice06.com/CN/Y2019/V45/I4/254

参考文献

［1］朱国策.基于深度卷积神经网络的医学图像肺结节检测方法研究［D］.无锡:江南大学,2017.
［2］周兵.CT影像中肺结节检测与识别方法的研究［D］.成都:电子科技大学,2017.
［3］胡伟俭,陈为,冯浩哲,等.应用于平扫CT图像肺结节检测的深度学习方法综述［J］.浙江大学学报(理学版),2017,44(4):379-384.
［4］KOSTIS W J,REEVES A P,YANKELEVITZ D F,et al.Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images［J］.IEEE Transactions on Medical Imaging,2013,22(10):1259-1274.
［5］GAO T,GONG J,WANG Y,et al.Three dimensional adaptive template matching algorithm for lung nodule detection［J］.Journal of Image and Graphics,2014,19(9):1384-1391.
［6］LIN D,YAN C R,CHEN W T.Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system［J］.Computerized Medical Imaging and Graphics,2005,29(6):447-458.
［7］HONG H,JIN M G.Automatic segmentation of ground-glass opacity nodule on chest CT images by histogram modeling and local contrast［C］//Proceedings of Radiological Society of North America 2012 Scientific Assembly and Annual Meeting.Berlin,Germany:Springer,2012:99-107.
［8］CHEN G H.Solving sobole active contour models via level set［C］//Proceedings of 2014 International Conference on Advanced Control,Automation and Robotics.New York,USA:ACM Press,2014:8-12.
［9］PAIK D S,BEAULIEU C F,RUBIN G D,et al.Surface normal overlap:a computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT［J］.IEEE Transactions on Medical Imaging,2004,23(6):661-667.
［10］KATSUMATA Y,ITAI Y S M.Automatic detection of GGO candidate regions employing four statistical features on thoracic MDCT image［C］//Proceedings of International Conference on Control,Automatic and System.New York,USA:ACM Press,2007:10-20.
［11］CHEN S,SUZUKI K,MACMAHON H.Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification［J］.Medical Physics,2011,38(4):1844-1858.
［12］CAMPADELLI P,CASIRAGHI E,ARTIOLI D.A fully automated method for lung nodule detection from postero-anterior chest radiographs［J］.IEEE Transactions on Medical Imaging,2006,25(12):1588-1603.
［13］SNOEREN P R,LITJENS G J S,GINNEKEN B V,et al.Training a computer aided detection system with simulated lung nodules in chest radiographs［C］//Proceedings of the 3rd International Workshop on Pulmonary Image Analysis.New York,USA:ACM Press,2016,139-142.
［14］孟以爽,易平,顾问,等.基于深度学习的肺结节检测［J］.计算机时代,2018(2):5-9.
［15］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.
［16］RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmenta-tion［EB/OL］.［2018-04-18］.https://arxiv.org/abs/1505.04597v1.
［17］GAO H,ZHUANG L.Densely connected convolutional networks［EB/OL］.［2018-04-18］.https://arxiv.org/abs/1608.06993
［18］陈鸿翔.基于卷积神经网络的图像语义分割［D］.杭州:浙江大学,2016.
［19］LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Computer Society,2015:3431-3440.
［20］芮杰.多源遥感数据测绘应用关键技术研究［D］.北京:中国科学院大学,2017.
［21］QIN P,LI C,CHEN J,et al.Research on improved algorithm of object detection based on feature pyramid［J］.Multimedia Tools and Applications,2019,78(1):913-927.
［22］LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection［EB/OL］.［2018-04-18］.https://arxiv.org/abs/1612.03144v2.
［23］LIN G H,LUO S W,HUANG Y P,et al.A novel regularization method based on convolution neural network［J］.Journal of Computer Research and Development,2014,51(9):1891-1900.
［24］DICE L R.Measures of the amount of ecologic association between species［J］.Ecology,1945,26(3):297-302.
［25］刘宝生,闫莉萍,周东华.几种相似性测度的比较［J］.计算机应用研究,2006,23(11):1-3.
［26］周清华,范亚光,王颖,等.中国肺部结节分类、诊断与治疗指南［J］.中国肺癌杂志,2016,19(12):793-798.

[1]	耿丽丽, 牛保宁. 基于通道相似度熵的卷积神经网络裁剪[J]. 计算机工程, 2024, 50(7): 133-143.
[2]	张洋, 刘畅, 李少青. 基于可控制性度量的图神经网络门级硬件木马检测方法[J]. 计算机工程, 2024, 50(7): 164-173.
[3]	牛瑞婷, 严天峰, 高锐, 王映植. 低信噪比下基于深度学习TCNN-MobileNet的调制识别[J]. 计算机工程, 2024, 50(7): 204-215.
[4]	张溢文, 蔡满春, 陈咏豪, 朱懿, 姚利峰. 融合空间特征的多尺度深度伪造检测方法[J]. 计算机工程, 2024, 50(7): 240-250.
[5]	逯焕宇, 张永宏, 马光义, 谢东林, 田伟. 基于半监督对抗学习的遥感图像水体提取[J]. 计算机工程, 2024, 50(7): 251-263.
[6]	肖慈, 徐杨, 张永丹, 冯明文, 黄易仟. 结合注意力和低光增强的夜间语义分割[J]. 计算机工程, 2024, 50(7): 271-281.
[7]	张诗婧, 莫绪涛, 赵行, 董杨林. 基于球面折反射成像和YOLOv7的内螺纹缺陷检测[J]. 计算机工程, 2024, 50(7): 282-292.
[8]	徐明亮, 李芳媛, 马浩然, 何飞. 大规模神经记录的峰电位聚类算法(特邀)[J]. 计算机工程, 2024, 50(6): 1-34.
[9]	魏琢艺, 罗迈, 李文兵, 曾远松, 余伟江, 杨跃东. 基于多源域适应的单细胞智能分类[J]. 计算机工程, 2024, 50(6): 48-55.
[10]	李子杰, 周菊香, 韩晓瑜, 甘健侯, 鹿泽光, 王俊. 序列特征与学习过程融合的知识追踪模型[J]. 计算机工程, 2024, 50(6): 77-85.
[11]	李永飞, 李铭洋, 常鑫, 曹可欣. 基于可解释性深度学习的物联网水质监测数据异常检测[J]. 计算机工程, 2024, 50(6): 179-187.
[12]	于洋, 孙芳芳, 吕华, 李扬, 王晓民. 基于多尺度时空注意力网络的微表情检测方法[J]. 计算机工程, 2024, 50(6): 228-235.
[13]	李致金, 汤佳辉, 闫金凤. 基于边缘计算的轻量化识别方法[J]. 计算机工程, 2024, 50(6): 287-295.
[14]	李雪, 王雅文, 张前进. 基于信息检索的源代码自动命名[J]. 计算机工程, 2024, 50(6): 304-310.
[15]	孙帮勇, 马铭, 于涛. 基于区域特征强化的多尺度伪装目标检测方法[J]. 计算机工程, 2024, 50(5): 209-219.

选择文件类型/文献管理软件名称

选择包含的内容