计算机科学 ›› 2020, Vol. 47 ›› Issue (9): 129-134.doi: 10.11896/jsjkx.190700203

• 计算机图形学&多媒体 • 上一篇    下一篇

多分支卷积神经网络肺结节分类方法及其可解释性

张佳嘉, 张小洪   

  1. 重庆大学大数据与软件学院 重庆400000
  • 收稿日期:2019-07-29 发布日期:2020-09-10
  • 通讯作者: 张小洪(xhongz@cqu.edu.cn)
  • 作者简介:gagazhang@cqu.edu.cn
  • 基金资助:
    国家自然科学基金(61772093);重庆市重大主题专项项目(cstc2018jszx-cyztzxX0017)

Multi-branch Convolutional Neural Network for Lung Nodule Classification and Its Interpretability

ZHANG Jia-jia, ZHANG Xiao-hong   

  1. School of Big Data & Software Engineering,Chongqing University,Chongqing 400000,China
  • Received:2019-07-29 Published:2020-09-10
  • About author:ZHANG Jia-jia,born in 1994,postgra-duate.Her main research interests include medical image analysis,deep learning and so on.
    ZHANG Xiao-hong,born in 1973,professor.His main research interests include data mining of software enginee-ring,topic modeling,image semantic analysis and video analysis.
  • Supported by:
    National Natural Science Foundation of China (61772093) and Chongqing Major Theme Projects (cstc2018jszx-cyztzxX0017).

摘要: 肺结节CT图像表征复杂且多样,导致对肺结节进行分类较为困难。虽然越来越多的深度学习模型被应用到计算机辅助肺癌诊断系统的肺结节分类任务中,但这些模型的“黑盒”特性无法解释模型从数据中学习到了哪些知识,以及这些知识是如何影响决策的,导致诊断结果缺乏可信性。为此,文中提出了一种可解释的多分支卷积神经网络模型来判别肺结节的良恶性。该模型利用医生诊断时所用的肺结节语义特征信息来辅助诊断肺结节的良恶性,并将这些特征与肺结节良恶性判别网络融合成多分支网络,在完成肺结节良恶性诊断任务的同时,得到肺结节相关语义特征的预测结果,为医生提供可信的诊断依据。在LIDC-IDRI数据集上的实验结果表明,与现有方法相比,所提模型不仅可以得到可解释的诊断结果,而且实现了更好的肺结节良恶性分类效果,其准确率可达97.8%。

关键词: 计算机辅助诊断, 卷积神经网络, 多分支, 可解释性, 肺结节恶性程度分类

Abstract: The characteristics of lung nodules are complex and diverse,which make it difficult to classify lung nodules.Although more and more deep learning models are applied to the lung nodule classification task of computer-aided lung cancer diagnosis systems,the “black box” characteristics of these models cannot explain what knowledge the model has learned from the data and how the knowledge influences the decision,leading to a lack of reliability in the diagnosis results.To this end,an interpretable multi-branch convolutional neural network model is proposed to identify the benign and malignant lung nodules.The model uses the semantic features of the pulmonary nodules which radiologists use in diagnosis to assist identifying the benign and malignant lung nodules.These characteristics are combined with the branch of malignancy classification into a multi-branch network.Then beyond the malignancy classification,the model can predict nodule attributes,which could potentially explain the diagnosis result.Experimental results on the LIDC-IDRI dataset show that,compared with the existing methods,the proposed model can not only obtain interpretable diagnostic results,but also achieve better classification of lung nodules with an accuracy rate of 97.8%.

Key words: Computer-aided diagnosis, Convolutional neural network, Multi-branch, Interpretable, Classification of malignant degree of pulmonary nodules

中图分类号: 

  • TP183
[1] SIEGEL R L,MILLER K D,JEMAL A.Cancer statistics,2016[J].CA:A Cancer Journal for Clinicians,2016,66(1):7-30.
[2] SHEN S,HAN S X,PETOUSIS P,et al.A Bayesian model for estimating multi-state disease progression[J].Computers in Biology and Medicine,2017,81:111-120.
[3] National Lung Screening Trial Research Team.Reduced lung-cancer mortality with low-dose computed tomographic screening[J].New England Journal of Medicine,2011,365(5):395-409.
[4] ARMATO III S G,ALTMAN M B,WILKIE J,et al.Automated lung nodule classification following automated nodule detection on CT:A serial approach[J].Medical Physics,2003,30(6):1188-1197.
[5] SHEN S,BUI A A T,CONG J,et al.An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy[J].Computers in Biology and Medicine,2015,57:139-149.
[6] DUGGAN N,BAE E,SHEN S,et al.A technique for lung nodule candidate detection in CT using global minimization methods[C]//International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition.Cham:Springer, 2015:478-491.
[7] FIRMINO M,ANGELO G,MORAIS H,et al.Computer-aided detection (CADe) and diagnosis (CADx) system for lung cancer with likelihood of malignancy[J].Biomedical Engineering Online,2016,15(1):2.
[8] AMIR G J,LEHMANN H P.After detection:The improvedaccuracy of lung cancer assessment using radiologic computer-aided diagnosis[J].Academic Radiology,2016,23(2):186-191.
[9] HUANG P,PARK S,YAN R,et al.Added value of computer-aided CT image features for early lung cancer diagnosis with small pulmonary nodules:a matched case-control study[J].Radiology,2017,286(1):286-295.
[10] SHEN W,ZHOU M,YANG F,et al.Multi-scale Convolutional Neural Networks for Lung Nodule Classification[J].Inf Process Med Imaging,2015,24:588-599.
[11] SHEN W,ZHOU M,YANG F,et al.Multi-crop Convolutional Neural Networks for Lung Nodule Malignancy Suspiciousness Classification[J].Pattern Recognition,2016,61(61):663-673.
[12] PIEDRA E A R,TAIRA R K,EL-SADEN S,et al.Assessing variability in brain tumor segmentation to improve volumetric accuracy and characterization of change[C]// IEEE-EMBS International Conference on Biomedical & Health Informatics.IEEE,2016.
[13] 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.
[14] LIANG C H,YUE J Y,HAN D M,et al.Diagnostic value of lobulation sign in solitary pulmonary nodule by CT to determine.
benignity or malignancy[J].Medical Information(Section of Operative Surgery),2007(10):94-95.
[15] HUSSEIN S,CAO K,SONG Q,et al.Risk stratification of lung nodules using 3d cnn-based multi-task learning[C]//International Conference on Information Processing in Medical Imaging.Cham:Springer, 2017:249-260.
[16] KIM H,PARK C M,GOO J M,et al.Quantitative Computed Tomography Imaging Biomarkers in the Diagnosis and Management of Lung Cancer[J].Investigative Radiology,2015,50(9).
[17] ARMATO S,MCLENNAN G,M MCNITT-GRAY,et al.WE-B-201B-02:The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI):A Completed Public Database of CT Scans for Lung Nodule Analysis[J].Medical Physics,2010,37(6Part6):3416-3417.
[18] MOLCHANOV P,TYREE S,KARRAS T,et al.Pruning Conv-olutional Neural Networks for Resource Efficient Inference[J].International Conference on Learning Representations,2017,2:324-332.
[19] CAUSEY J,ZHANG J Y,MA S Q,et al.Highly accurate model for prediction of lung nodule malignancy with CT scans[J].Scientific Reports,2018,8(1):9286.
[20] XIE Y,ZHANG J,XIA Y,et al.Fusing texture,shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT[J].Information Fusion,2018,42:102-110.
[1] 单美静, 秦龙飞, 张会兵. L-YOLO:适用于车载边缘计算的实时交通标识检测模型[J]. 计算机科学, 2021, 48(1): 89-95.
[2] 何彦辉, 吴桂兴, 吴志强. 基于域适应的X光图像的目标检测[J]. 计算机科学, 2021, 48(1): 175-181.
[3] 李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述[J]. 计算机科学, 2021, 48(1): 209-216.
[4] 朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价[J]. 计算机科学, 2020, 47(9): 150-156.
[5] 崔彤彤, 王桂玲, 高晶. 基于1DCNN-LSTM的船舶轨迹分类方法[J]. 计算机科学, 2020, 47(9): 175-184.
[6] 刘海潮, 王莉. 基于深度图卷积胶囊网络的图分类模型[J]. 计算机科学, 2020, 47(9): 219-225.
[7] 梁正友, 何景琳, 孙宇. 一种用于微表情自动识别的三维卷积神经网络进化方法[J]. 计算机科学, 2020, 47(8): 227-232.
[8] 孙彦丽, 叶炯耀. 基于剪枝与量化的卷积神经网络压缩方法[J]. 计算机科学, 2020, 47(8): 261-266.
[9] 程哲, 白茜, 张浩, 王世普, 梁宇. 使用深层卷积神经网络提高Hi-C 数据分辨率[J]. 计算机科学, 2020, 47(6A): 70-74.
[10] 赫磊, 邵展鹏, 张剑华, 周小龙. 基于深度学习的行为识别算法综述[J]. 计算机科学, 2020, 47(6A): 139-147.
[11] 孙正, 王新宇. 深度学习在光声成像中的应用现状[J]. 计算机科学, 2020, 47(6A): 148-152.
[12] 马海江. 基于卷积神经网络与约束概率矩阵分解的推荐算法[J]. 计算机科学, 2020, 47(6A): 540-545.
[13] 王燕, 王丽. 面向高光谱图像分类的局部Gabor卷积神经网络[J]. 计算机科学, 2020, 47(6): 151-156.
[14] 汪航, 陈晓, 田晟兆, 陈端兵. 基于小样本学习的SAR图像识别[J]. 计算机科学, 2020, 47(5): 124-128.
[15] 蔡强, 邓毅彪, 李海生, 余乐, 明少锋. 基于深度学习的人体行为识别方法综述[J]. 计算机科学, 2020, 47(4): 85-93.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[2] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[3] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .
[4] 杨羽琦,章国安,金喜龙. 车载自组织网络中基于车辆密度的双簇头路由协议[J]. 计算机科学, 2018, 45(4): 126 -130 .
[5] 施超,谢在鹏,柳晗,吕鑫. 基于稳定匹配的容器部署策略的优化[J]. 计算机科学, 2018, 45(4): 131 -136 .
[6] 韩奎奎,谢在鹏,吕鑫. 一种基于改进遗传算法的雾计算任务调度策略[J]. 计算机科学, 2018, 45(4): 137 -142 .
[7] 郑秀林,宋海燕,付伊鹏. MORUS-1280-128算法的区分分析[J]. 计算机科学, 2018, 45(4): 152 -156 .
[8] 吴姝,周安民,左政. PDiOS:iOS应用程序中私有API的调用检测[J]. 计算机科学, 2018, 45(4): 163 -168 .
[9] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[10] 罗霄阳,霍宏涛,王梦思,陈亚飞. 基于多残差马尔科夫模型的图像拼接检测[J]. 计算机科学, 2018, 45(4): 173 -177 .