基于深度学习的肺炎图像目标检测

doi:10.3969/j.issn.0258-8021.2022.04.007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7432 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Pneumonia is a disease that seriously endangers people′s health. Lung X-rays are usually used for pneumonia examination. The diagnosis of pneumonia is a very important step before the treatment of pneumonia. However, due to the interference of other lung diseases, the explosion of medical data, and the lack of professional pathologists, it is very difficult to accurately diagnose pneumonia. Deep learning can imitate the mechanism of the human brain to interpret medical image datasets with improved accuracy and efficiency, therefore, has been widely used in pneumonia image detection. In this paper, three deep learning-based object detection models, SSD, faster-RCNN and faster-RCNN optimization model, were used to study 26 684 labeled lung X-ray images from the Kaggle dataset. The original X-ray images were preprocessed and then input into the three deep learning models to detect single or two lesion areas. The performance of the three models was evaluated and compared through loss function, classification accuracy, regression accuracy and number of mis-detected lesions by testing 500 randomly selected images. The results showed that faster-RCNN performed better than SSD in performance metrics; Faster-RCNN optimization model was superior to the other two models with the loss value that was small and could quickly reach stability, the average classification accuracy of 93.7%, the average regression accuracy of 79.8% and the number of mis-detected lesions of 0, which would be helpful for the accurate identification and diagnosis of pneumonia.

Key words： object detection pneumonia image deep learning faster region-based convolutional neural network (faster-RCNN) model single shot multibox detector (SSD) model

Received: 28 August 2021

PACS:

R318

Corresponding Authors: ^*E-mail:lxliu@xidian.edu.cn; zhangzhoufeng@opt.ac.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	He Di
	Liu Lixin
	Liu Yujie
	Xiong Feng
	Qi Meijie
	Zhang Zhoufeng

Cite this article:

He Di,Liu Lixin,Liu Yujie, et al. Object Detection of Pneumonia Images Based on Deep Learning[J]. Chinese Journal of Biomedical Engineering, 2022, 41(4): 443-451.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2022.04.007 OR http://cjbme.csbme.org/EN/Y2022/V41/I4/443

[1] Xu JQ, Murphy SL, Kochanek KD, et al. Deaths: final data for 2019. National Vital Statistics Reports, 70(8): 1-86[EB/OL]. https://www.cdc.gov/nchs/data/nvsr/nvsr70/nvsr70-08-508.pdf, 2021-07-26/2021-08-26.
[2] 百度. 疫情实时大数据报告[EB/OL]. https://voice.baidu.com/act/newpneumonia/newpneumonia/, 2021-08-26/2021-08-26.
[3] Goodfellow I, Bengio Y, Courville A. Deep learning[M]. Cambridge: MIT Press, 2016: 326-366.
[4] Xiong Feng, He Di, Liu Yujie, et al. Pneumonia image classification based on convolutional neural network[J]. Proc SPIE, 2021, 12057: 120573C.
[5] Xiong Feng, He Di, Liu Yujie, et al. Classification of pneumonia images based on improved VGG19 convolutional neural network[J]. Acta Photonica Sinica, 2021, 50(10): 1010001.
[6] 马书浩, 安居白. 基于YOLOv3改进的肺炎检测算法[J]. 激光与光电子学进展, 2020, 57(18): 310-316.
[7] Nurmaini S, Tondas AE, Partan RU, et al. Automated detection of covid-19 infected lesion on computed tomography images using Faster-RCNNs[J]. Engineering Letters, 2020, 28(4): 1295-1301.
[8] Dharani MK, Santhoshkumar S, Balaji T. Detection of pneumonia from X-ray imaging using Faster RCNN[J]. International Journal of Control and Automation, 2020, 13(2): 227-234.
[9] Yu Liang, Li Binbin, Jiao Bin. Research and Implementation of CNN Based on TensorFlow[J]. IOP Conference Series: Materials Science and Engineering, 2019, 490: 042022.
[10] Pang Bo, Nijkamp E, Wu Yingnian. Deep learning with TensorFlow: a review[J]. Journal of Educational and Behavioral Statistics, 2020, 45(2): 227-248.
[11] 王彦辰. 基于多尺度数字X光图像增强方法的研究[D]. 北京:中国科学院研究生院, 2005.
[12] 黄元忠, 廖小华, 卢庆华. 结合双线性插值与局部均值的红外图像插值算法[J]. 计算技术与自动化, 2020, 39(2): 134-137.
[13] 张久鹏, 张伟. 基于反转的限制对比度自适应直方图均衡图像去雾改进算法[J]. 物联网技术, 2015, 5(2): 10-16.
[14] Jeon G. Denoising in Contrast-Enhanced X-ray images[J]. Sensing and Imaging, 2016, 17(14): 1-11.
[15] Liu Wei, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector[C]//The 14th European Conference on Computer Vision (ECCV). Amsterdam: Springer, Cham, 2016: 21-37.
[16] Kang Yixuan. Research on SSD base network[J]. IOP Conference Series: Materials Science and Engineering, 2020, 768: 072031.
[17] Ren Shaoqing, He Kaiming, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[18] 高智勇, 黄金镇, 杜成刚. 基于特征金字塔网络的肺结节检测[J]. 计算机应用, 2020, 40(9): 2571-2576.
[19] 曹盼, 刘哲, 王斐, 等. 特征金字塔在胸部 X 射线图像上筛检肺结核的价值[J]. 中国防痨杂志, 2019, 41(3): 288-293.
[20] Lee SG, Bae JS, Kim H, et al. Liver lesion detection from weakly-labeled multi-phase CT volumes with a grouped single shot multibox detector[C]//The 21st International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Granada: Springer, 2018: 693-701.
[21] Yao Shangjie, Chen Yaowu, Tian Xiang, et al. Pneumonia detection using an improved algorithm based on Faster R-CNN[J]. Computational and Mathematical Methods in Medicine, 2021, 2021(3): 8854892.
[22] Kallet RH. The vexing problem of ventilator-associated pneumonia: observations on pathophysiology, public policy, and clinical science[J]. Respiratory Care, 2015, 60 (10): 1495-1508.