A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images
Source abstract
Abstract
Pneumonia is among the top diseases which cause most of the deaths all over the world. Virus, bacteria and fungi can all cause pneumonia. However, it is difficult to judge the pneumonia just by looking at chest X-rays. The aim of this study is to simplify the pneumonia detection process for experts as well as for novices. We suggest a novel deep learning framework for the detection of pneumonia using the concept of transfer learning. In this approach, features from images are extracted using different neural network models pretrained on ImageNet, which then are fed into a classifier for prediction. We prepared five different models and analyzed their performance. Thereafter, we proposed an ensemble model that combines outputs from all pretrained models, which outperformed individual models, reaching the state-of-the-art performance in pneumonia recognition. Our ensemble model reached an accuracy of 96.4% with a recall of 99.62% on unseen data from the Guangzhou Women and Children’s Medical Center dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: COVID-19 diagnosis using AI · AI in cancer detection · Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Lovely Professional University, Punjab 144411, India
Maharaja Agrasen Institute of Technology, New Delhi 110034, India
Department of Information Engineering, University of Padova, 35131 Padova, Italy
School of Information Systems, Science and Engineering Faculty, Queensland University of Technology, Brisbane City 4000 QLD, Australia
Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland
Graduate Program in Applied Informatics, University of Fortaleza, Fortaleza 60811-905, CE, Brazil
References (66)
Show source-provided references
1. Exploiting Convolutional Neural Networks With Deeply Local Description for Remote Sensing Image Classification10.1109/ACCESS.2018.2798799 ↗
2. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
3. Computer-assisted frameworks for classification of liver, breast and blood neoplasias via neural networks: A survey based on medical images10.1016/j.neucom.2018.06.080 ↗
4. Asiri, N., Hussain, M., Al Adel, F., and Alzaidi, N. (2019). Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey. Artif. Intell. Med., 99.10.1016/j.artmed.2019.07.009 ↗
5. Effective feature learning and fusion of multimodality data using stage-wise deep neural network for dementia diagnosis10.1002/hbm.24428 ↗
6. Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis10.1109/JBHI.2017.2767063 ↗
7. Survey on deep learning for radiotherapy10.1016/j.compbiomed.2018.05.018 ↗
8. Real time path finding for assisted living using deep learning
9. Zhang, X., Yao, L., Wang, X., Monaghan, J., and McAlpine, D. (2019). A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers. arXiv.
10. Bakator, M., and Radosav, D. (2018). Deep Learning and Medical Diagnosis: A Review of Literature. Multimodal Technol. Interact., 2.10.3390/mti2030047 ↗
11. A literature review and survey of childhood pneumonia etiology studies: 2000–201010.1093/cid/cir1053 ↗
12. Recently published papers: Pneumonia, hypothermia and the elderly10.1186/cc5049 ↗
13. Pneumonia research to reduce childhood mortality in the developing world10.1172/JCI33947 ↗
14. Advances in the causes and management of community acquired pneumonia in adults10.1136/bmj.j2471 ↗
15. (2019, November 21). National Center for Health Statistics (NCHS); Centers for Disease Control and Prevention (CDC) FastStats: Pneumonia, Available online: http://www.cdc.gov/nchs/fastats/pneumonia.htm.
16. Deaths: Leading causes for 2010
17. World Health Organization (2017). The Top 10 Causes of Death, World Health Organization. Available online: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death.
18. How far have we come? Artificial intelligence for chest radiograph interpretation10.1016/j.crad.2018.12.015 ↗
19. Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., and Summers, R.M. (2017, January 21–26). Chestx-ray8: Hospital scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.369 ↗
20. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
21. Roth, H.R., Lu, L., Seff, A., Cherry, K.M., Hoffman, J., Wang, S., Liu, J., Turkbey, E., and Summers, R.M. (2014, January 14–18). A new 2.5 d representation for lymph node detection using random sets of deep convolutional neural network observations. Proceedings of the 17th International Conference on Medical Image Computing and Computer-Assisted Intervention, Boston, MA, USA.10.1007/978-3-319-10404-1_65 ↗
22. Deep convolutional neural networks for computer-aided detection: Cnn architectures, dataset characteristics and transfer learning10.1109/TMI.2016.2528162 ↗
23. Rajpurkar, P., Irvin, J., Ball, R.L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., and Langlotz, C.P. (2018). Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med., 15.10.1371/journal.pmed.1002686 ↗
24. Small lung nodules detection based on local variance analysis and probabilistic neural network10.1016/j.cmpb.2018.04.025 ↗
25. Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs10.1016/j.compbiomed.2018.10.011 ↗
26. Ho, T.K.K., and Gwak, J. (2019). Multiple feature integration for classification of thoracic disease in chest radiography. Appl. Sci., 9.10.3390/app9194130 ↗
27. Identifying pneumonia in chest X-rays: A deep learning approach10.1016/j.measurement.2019.05.076 ↗
28. Jung, H., Kim, B., Lee, I., Lee, J., and Kang, J. (2018). Classification of lung nodules in CT scans using three-dimensional deep convolutional neural networks with a checkpoint ensemble method. BMC Med. Imaging, 18.10.1186/s12880-018-0286-0 ↗
29. Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks10.1148/radiol.2017162326 ↗
30. Li, X., Shen, L., Xie, X., Huang, S., Xie, Z., Hong, X., and Yu, J. (2019). Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detection. Artif. Intell. Med., 101744.10.1016/j.artmed.2019.101744 ↗
31. Liang, G., and Zheng, L. (2019). A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Comput. Methods Programs Biomed., 104964.10.1016/j.cmpb.2019.06.023 ↗
32. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs10.1148/radiol.2018180237 ↗
33. Nasrullah, N., Sang, J., Alam, M.S., Mateen, M., Cai, B., and Hu, H. (2019). Automated lung nodule detection and classification using deep learning combined with multiple strategies. Sensors, 19.10.3390/s19173722 ↗
34. Efficient deep network architectures for fast chest X-ray tuberculosis screening and visualization10.1038/s41598-019-42557-4 ↗
35. 3-D convolutional neural networks for automatic detection of pulmonary nodules in chest CT10.1109/JBHI.2018.2879449 ↗
36. Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database10.1016/j.compeleceng.2019.08.004 ↗
37. An automatic method for lung segmentation and reconstruction in chest X-ray using deep neural networks10.1016/j.cmpb.2019.06.005 ↗
38. Taylor, A.G., Mielke, C., and Mongan, J. (2018). Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. PLoS Med., 15.10.1371/journal.pmed.1002697 ↗
39. Lung nodule detection in CT images using a raw patch-based convolutional neural network10.1007/s10278-019-00221-3 ↗
40. Xiao, Z., Du, N., Geng, L., Zhang, F., Wu, J., and Liu, Y. (2019). Multi-scale heterogeneous 3D CNN for false-positive reduction in pulmonary nodule detection, based on chest CT images. Appl. Sci., 9.10.3390/app9163261 ↗
41. Semi-supervised adversarial model for benign–malignant lung nodule classification on chest CT10.1016/j.media.2019.07.004 ↗
42. CXNet-m1: Anomaly detection on chest X-rays with image-based deep learning10.1109/ACCESS.2018.2885997 ↗
43. Machine learning “red dot”: Open-source, cloud, deep convolutional neural networks in chest radiograph binary normality classification10.1016/j.crad.2018.05.015 ↗
44. da Nóbrega, R.V.M., Rebouças Filho, P.P., Rodrigues, M.B., da Silva, S.P.P., Dourado Júnior, C.M.J.M., and de Albuquerque, V.H.C. (2018). Lung nodule malignancy classification in chest computed tomography images using transfer learning and convolutional neural networks. Neural Comput. Appl., 1–18.10.1007/s00521-018-3895-1 ↗
45. A neuro-heuristic approach for recognition of lung diseases from X-ray images10.1016/j.eswa.2019.01.060 ↗
46. Deep learning, reusable and problem-based architectures for detection of consolidation on chest X-ray images10.1016/j.cmpb.2019.105162 ↗
47. BIRNet: Brain image registration using dual-supervised fully convolutional networks10.1016/j.media.2019.03.006 ↗
48. Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017, January 21–23). Understanding of a convolutional neural network. Proceedings of the 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey.10.1109/ICEngTechnol.2017.8308186 ↗
49. Goyal, M., Goyal, R., and Lall, B. (2019). Learning Activation Functions: A new paradigm of understanding Neural Networks. arXiv.10.1007/978-3-030-31760-7_1 ↗
50. Bailer, C., Habtegebrial, T., Varanasi, K., and Stricker, D. (2018). Fast Feature Extraction with CNNs with Pooling Layers. arXiv.
51. Yosinski, J., Clune, J., Bengio, Y., Lipson, H., Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. (2014). How transferable are features in deep neural networks?. Advances in Neural Information Processing Systems 27, Proceedings of the Neural Information Processing Systems 2014, Montreal, QC, Canada, 8–13 December 2014, Neural Information Processing Systems Foundation, Inc. (NIPS).
52. Dai, W., Chen, Y., Xue, G.-r., Yang, Q., Yu, Y., Koller, D., Schuurmans, D., Bengio, Y., and Bottou, L. (2008). Translated Learning: Transfer Learning across Different Feature Spaces. Advances in Neural Information Processing Systems 21, Proceedings of the Neural Information Processing Systems 2008, Vancouver, BC, Canada, 8–10 December 2008, Neural Information Processing Systems Foundation, Inc. (NIPS).
53. Raghu, M., Zhang, C., Kleinberg, J.M., and Bengio, S. (2019). Transfusion: Understanding Transfer Learning with Applications to Medical Imaging. arXiv.
54. Carneiro, G. (2016). Understanding the Mechanisms of Deep Transfer Learning for Medical Images. Deep Learning and Data Labeling for Medical Applications, Springer. DLMIA 2016, LABELS 2016.10.1007/978-3-319-46976-8 ↗
55. ImageNet Classification with Deep Convolutional Neural Networks10.1145/3065386 ↗
56. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks. arXiv.10.1109/CVPR.2017.243 ↗
57. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
58. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. arXiv.10.1109/CVPR.2016.308 ↗
59. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2014). Going Deeper with Convolutions. arXiv.10.1109/CVPR.2015.7298594 ↗
60. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
61. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA.
62. Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning10.1016/j.cell.2018.02.010 ↗
63. Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference for Learning Representations, ICLR 2015, San Diego, CA, USA.
64. Cohen, J.P., Bertin, P., and Frappier, V. (2019). Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System. arXiv.
65. Causability and explainability of artificial intelligence in medicine10.1002/widm.1312 ↗
66. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗