Pneumonia image recognition model based on deep neural network

doi:10.11772/j.issn.1001-9081.2018102112

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (6): 1680-1684.DOI: 10.11772/j.issn.1001-9081.2018102112

• Artificial intelligence • Previous Articles Next Articles

Pneumonia image recognition model based on deep neural network

HE Xinyu^1,2,3, ZHANG Xiaolong^1,2,3

1. School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430065, China;
2. Institute of Big Data Science and Engineering, Wuhan University of Science and Technology, Wuhan Hubei 430065, China;
3. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan Hubei 430065, China

Received:2018-10-19 Revised:2018-12-21 Online:2019-06-17 Published:2019-06-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61273225, 61702381).

基于深度神经网络的肺炎图像识别模型

何新宇^1,2,3, 张晓龙^1,2,3

1. 武汉科技大学计算机科学与技术学院, 武汉 430065;
2. 武汉科技大学大数据科学与工程研究院, 武汉 430065;
3. 智能信息处理与实时工业系统湖北省重点实验室, 武汉 430065

通讯作者: 张晓龙
作者简介:何新宇(1993-),男,湖北咸宁人,硕士研究生,主要研究方向:计算机视觉、深度学习;张晓龙(1963-),男,江西吉安人,教授,博士,主要研究方向:人工智能和机器学习、数据挖掘、生物信息处理。
基金资助:
国家自然科学基金资助项目（61273225，61702381）。

Abstract

Abstract: Current recognition algorithm of pneumonia image faces two problems. First, the extracted features can not fit the pneumonia image well because the transfer learning model used by the pneumonia feature extractor has large image difference between the source dataset and the pneumonia dataset. Second, the softmax classifier used by the algorithm can not well process high-dimensional features, and there is still room for improvement in recognition accuracy. Aiming at these two problems, a pneumonia image recognition algorithm based on Deep Convolution Neural Network (DCNN) was proposed. Firstly, the GoogLeNet Inception V3 network model trained by ImageNet dataset was used to extract the features. Then, a feature fusion layer was added and random forest classifier was used to classify and forecast. Experiments were implemented on Chest X-Ray Images pneumonia standard dataset. The experimental results show that the recognition accuracy, sensitivity and specificity of the proposed model reach 96.77%, 97.56% and 94.26% respectively. The proposed model is 1.26 percentage points and 1.46 percentage points higher than the classic GoogLeNet Inception V3+Data Augmentation (GIV+DA) algorithm in the index of recognition accuracy and sensitivity, and is close to the optimal result of GIV+DA in the index of specificity.

Key words: pneumonia image classification, transfer learning, Deep Convolution Neural Network (DCNN), random forest, sensitivity, specificity

摘要： 当前的肺炎图像识别算法面临两个问题：一是肺炎特征提取器使用的迁移学习模型在源数据集与肺炎数据集上图像差异较大，所提取的特征不能很好地契合肺炎图像；二是算法使用的softmax分类器对高维特征处理能力不够强，在识别准确率上仍有提升的空间。针对这两个问题，提出了一种基于深度卷积神经网络的肺炎图像识别模型。首先使用ImageNet数据集训练好的GoogLeNet Inception V3网络模型进行特征提取；其次，增加了特征融合层，使用随机森林分类器进行分类预测。实验在Chest X-Ray Images肺炎标准数据集上进行。实验结果表明，该模型的识别准确率、敏感度、特异度的值分别达到96.77%、97.56%、94.26%。在识别准确率以及敏感度指标上，与经典的GoogLeNet Inception V3+Data Augmentation （GIV+DA）算法相比，所提模型分别提高了1.26、1.46个百分点，在特异度指标上已接近GIV+DA算法的最优结果。

关键词: 肺炎图像分类, 迁移学习, 深度卷积神经网络, 随机森林, 敏感度, 特异度

CLC Number:

TP391.4

HE Xinyu, ZHANG Xiaolong. Pneumonia image recognition model based on deep neural network[J]. Journal of Computer Applications, 2019, 39(6): 1680-1684.

何新宇, 张晓龙. 基于深度神经网络的肺炎图像识别模型[J]. 计算机应用, 2019, 39(6): 1680-1684.

References

[1] RAJPURKAR P, IRVIN J, ZHU K, et al. CheXNet:radiologist-level pneumonia detection on chest X-rays with deep learning[EB/OL]. https://arxiv.org/pdf/1711.05225.pdf.
[2] RINALDI P, MENCHINI L, MARTINELLI M, et al. Computer-aided diagnosis[J]. Rays, 2003, 28(1):103-108.
[3] ZHAO G, AHONEN T, MATAS J, et al. Rotation-invariant image and video description with local binary pattern features[J]. IEEE Transactions on Image Processing, 2011, 21(4):1465-1477.
[4] 吕洪艳,刘芳.组合核函数SVM在特定领域文本分类中的应用[J].计算机系统应用,2016,25(5):124-128.(LYU H Y, LIU F. Application of text classification for specific domains based on combination kernel function SVM[J]. Computer Systems & Applications, 2016, 25(5):124-128.)
[5] HERSHEY S, CHAUDHURI S, ELLIS D P W, et al. CNN architectures for largescale audio classification[C]//Proceedings of the 2017 IEEE International Conference on Acoustic, Speech and Signal Processing. Piscataway, NJ:IEEE, 2017:131-135.
[6] 刘长征,相文波.基于改进卷积神经网络的肺炎影像判别[J].计算机测量与控制,2017,25(4):185-188.(LIU C Z, XIANG W B. Recognition of pneumonia type based on improved convolution neural network[J]. Computer Measurement & Control, 2017, 25(4):185-188.)
[7] KERMANY D S, GOLDBAUM M, CAI W J, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5):1122-1131.
[8] VIANNA V P. Study and development of a computer-aided diagnosis system for classification of chest X-ray images using convolutional neural networks pre-trained for ImageNet and data augmentation[EB/OL].[2018-09-16]. https://arxiv.org/pdf/1806.00839v1.pdf.
[9] BALLESTER P, ARAUJO R M. On the performance of GoogLeNet and AlexNet applied to sketches[C]//AAAI 2016:Proceedings of the 2016 Thirtieth AAAI Conference on Artificial Intelligence. Menlo Park, CA:AAAI, 2016:1124-1128.
[10] MCDONNELL M D, VLADUSICH T. Enhanced image classification with a fast-learning shallow convolutional neural network[C]//Proceedings of the 2015 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2015:1-7.
[11] GAUDART J, GIUSIANO B, HUIART L. Comparison of the performance of multi-layer perceptron and linear regression for epidemiological data[J]. Computational Statistics & Data Analysis, 2004, 44(4):547-570.
[12] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:1-9.
[13] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//NIPS 2012:Proceedings of the 25th International Conference on Neural Information Processing Systems. North Miami Beach, FL:Curran Associates Inc., 2012:1097-1105.
[14] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2016:770-778.
[15] ZHANG C L, LUO J H, WEI X S, et al. In defense of fully connected layers in visual representation transfer[C]//PCM 2017:Proceedings of the 201718th Pacific Rim Conference on Multimedia, LNCS 10736. Cham:Springer, 2017:807-817.
[16] YUAN J W, YU S C. Privacy preserving back-propagation neural network learning made practical with cloud computing[J]. IEEE Transactions on Parallel and Distributed Systems, 2014, 25(1):212-221.
[17] MORSE G, STANLEY K O. Simple evolutionary optimization can rival stochastic gradient descent in neural networks[C]//GECCO 2016:Proceedings of the 2016 Genetic and Evolutionary Computation Conference. New York:ACM, 2016:477-484.
[18] ARTSTEIN-AVIDAN S, KÖNIG H, MILMAN V. The chain rule as a functional equation[J]. Journal of Functional Analysis, 2010, 259(11):2999-3024.
[19] BREIMAN L, LAST M, RICE J. Random forests:finding quasars[M]//FEIGELSON E D, BABU G J. Statistical Challenges in Astronomy. New York:Springer, 2003:243-254.
[20] PRUSA J D, KHOSHGOFTAAR T M, NAPOLITANO A. Using feature selection in combination with ensemble learning techniques to improve tweet sentiment classification performance[C]//ICTAI 2015:Proceedings of the 2015 IEEE 27th International Conference on Tools with Artificial Intelligence. Washington, DC:IEEE Computer Society, 2015:186-193.
[21] BREIMAN L I, FRIEDMAN J H, OLSHEN R A, et al. Classification and Regression Trees (CART)[J]. Encyclopedia of Ecology, 2015, 57(1):582-588.
[22] REN X D, GUO H N, LI S H, et al. A novel image classification method with CNN-XGBoost model[C]//IWDW 2017:Proceedings of the 2017 International Workshop on Digital Watermarking, LNCS 10431. Cham:Springer, 2017:378-390.

Pneumonia image recognition model based on deep neural network

基于深度神经网络的肺炎图像识别模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	ZHANG Yang, DONG Shicheng. Intelligent recommendation method for lock mechanism in concurrent program [J]. Journal of Computer Applications, 2021, 41(6): 1597-1603.
[2]	CHEN Zhengtao, HUANG Can, YANG Bo, ZHAO Li, LIAO Yong. Yak face recognition algorithm of parallel convolutional neural network based on transfer learning [J]. Journal of Computer Applications, 2021, 41(5): 1332-1336.
[3]	YU Dongchang, ZHAO Wenfang, NIE Kai, ZHANG Ge. Visibility forecast model based on LightGBM algorithm [J]. Journal of Computer Applications, 2021, 41(4): 1035-1041.
[4]	WANG Jinkai, JIA Xu. Vein recognition algorithm based on Siamese nonnegative matrix factorization with transferability [J]. Journal of Computer Applications, 2021, 41(3): 898-903.
[5]	Xiaolong LIU, Shitong WANG. Open set fuzzy domain adaptation algorithm via progressive separation [J]. Journal of Computer Applications, 2021, 41(11): 3127-3131.
[6]	Jianfang CAO, Minmin YAN, Yiming JIA, Xiaodong TIAN. Application of Inception-v3 model integrated with transfer learning in dynasty identification of ancient murals [J]. Journal of Computer Applications, 2021, 41(11): 3219-3227.
[7]	Jin ZHAO, Wen’ai SONG, Jun TAI, Jijiang YANG, Qing WANG, Xiaodan LI, Yi LEI, Yue QIU. Review of computer-aided face diagnosis for obstructive sleep apnea in children [J]. Journal of Computer Applications, 2021, 41(11): 3394-3401.
[8]	ZHANG Zenghui, JIANG Gaoxia, WANG Wenjian. Label noise filtering method based on local probability sampling [J]. Journal of Computer Applications, 2021, 41(1): 67-73.
[9]	ZHOU Xiang, ZHAI Junhai, HUANG Yajie, SHEN Ruicai, HOU Yingzhen. Instance selection algorithm for big data based on random forest and voting mechanism [J]. Journal of Computer Applications, 2021, 41(1): 74-80.
[10]	HUANG Xueyu, XU Haote, TAO Jianwen. Multi-source adaptation classification framework with feature selection [J]. Journal of Computer Applications, 2020, 40(9): 2499-2506.
[11]	ZHANG Chenxi, TANG Shu, TANG Ke. Strategies of parameter fault detection for rocket engines based on transfer learning [J]. Journal of Computer Applications, 2020, 40(9): 2774-2780.
[12]	XIAO Yuelei, ZHANG Yunjiao. Terrorist attack organization prediction method based on feature selection and hyperparameter optimization [J]. Journal of Computer Applications, 2020, 40(8): 2262-2267.
[13]	BAI Ruyi, GUO Xiaoying, JIA Chunhua. Sentiment prediction of small sample abstract painting image based on feature fusion [J]. Journal of Computer Applications, 2020, 40(8): 2207-2213.
[14]	NIE Xichan, ZHANG Yang, YU Dunhui, ZHANG Xingsheng. Spatial crowdsourcing task allocation algorithm for global optimization [J]. Journal of Computer Applications, 2020, 40(7): 1950-1958.
[15]	MA Jinlin, WEI Meng, MA Ziping. Pulmonary nodule segmentation method based on deep transfer learning [J]. Journal of Computer Applications, 2020, 40(7): 2117-2125.