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

所属专题: 医学图像

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

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

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] 王明, 武文芳, 王大玲, 冯时, 张一飞.
生成链接树:一种高数据真实性的反事实解释生成方法
Generative Link Tree:A Counterfactual Explanation Generation Approach with High Data Fidelity
计算机科学, 2022, 49(9): 33-40. https://doi.org/10.11896/jsjkx.220300158
[2] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[3] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[4] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[5] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[6] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[7] 张颖涛, 张杰, 张睿, 张文强.
全局信息引导的真实图像风格迁移
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[8] 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮.
基于DNGAN的磁共振图像超分辨率重建算法
Super-resolution Reconstruction of MRI Based on DNGAN
计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[9] 刘月红, 牛少华, 神显豪.
基于卷积神经网络的虚拟现实视频帧内预测编码
Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network
计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179
[10] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[11] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[12] 杨玥, 冯涛, 梁虹, 杨扬.
融合交叉注意力机制的图像任意风格迁移
Image Arbitrary Style Transfer via Criss-cross Attention
计算机科学, 2022, 49(6A): 345-352. https://doi.org/10.11896/jsjkx.210700236
[13] 杨健楠, 张帆.
一种结合双注意力机制和层次网络结构的细碎农作物分类方法
Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure
计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169
[14] 王杉, 徐楚怡, 师春香, 张瑛.
基于CNN-LSTM的卫星云图云分类方法研究
Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM
计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177
[15] 孙福权, 崔志清, 邹彭, 张琨.
基于多尺度特征的脑肿瘤分割算法
Brain Tumor Segmentation Algorithm Based on Multi-scale Features
计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!