Abstract
Tuberculosis is a contagious disease and is one of the leading causes of death especially in low and middle income countries such as Uganda. While there are several ways to diagnose tuberculosis, sputum smear microscopy is the commonest method practised. However, this method can be error prone and also requires trained medical personnel who are not always readily available. In this research, we apply deep learning models based on two pre-trained Convolutional Neural Networks: VGGNet and GoogLeNet Inception v3 to diagnose tuberculosis from 148 Ziehl-Neelsen stained sputum smear microscopic images from two different datasets. These networks are used in three different scenarios, namely, fast feature extraction without data augmentation, fast feature extraction with data augmentation and fine-tuning. Our results show that using Inception v3 for fast feature extraction without data augmentation produces the best results with an accuracy score of 86.7%. This provides a much better approach to disease diagnosis based on the use of diverse datasets from different sources and the results of this work can be leveraged in medical imaging for faster tuberculosis diagnosis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Activation functions in Neural Networks. https://www.geeksforgeeks.org/activation-functions-neural-networks/
Adgaonkar, A., Atreya, A., Mulgund, A.D., Nath, J.R.: Identification of Tuberculosis Bacilli using Image Processing. Int. J. Comput. Appl. (IJCA) ICONET-2014, 0975–8887 (2014)
A Beginners Guide to Convolutional Neural Networks (CNNs). https://skymind.ai/wiki/convolutional-network
Bakatoor, M., Radosav, D.: Deep learning and medical diagnosis: a review of literature. Multimodal Technol. Interact. 2(3) (2018). https://doi.org/10.3390/mti2030047
Bwambale, T.: Tuberculosis prevalence rises by 60% survey. http://www.newvision.co.ug/newvision/news/1460677/tuberculosis-prevalence-rises-survey
Damien: How to split a dataset. https://www.beyondthelines.net/machine-learning/how-to-split-a-dataset
Fogel, N.: Tuberculosis: a disease without boundaries. Tuberculosis 95(5), 527–531 (2015). https://doi.org/10.1016/j.tube.2015.05.017
Gupta, D.S.: Transfer learning & The art of using Pre-trained Models in Deep Learning. https://www.analyticsvidhya.com/blog/2017/06/transfer-learning-the-art-of-fine-tuning-a-pre-trained-model
Health Access Corps “Healthcare in Uganda. Lets do the numbers. http://healthaccesscorps.org/blog/2014/12/3/healthcare-in-uganda-lets-do-the-numbers
Kant, S., Srivastava, M.M.: Towards automated tuberculosis detection using deep learning. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp.1250-1253. IEEE, Bangalore, India (2018). https://doi.org/10.1109/SSCI.2018.8628800
Karpathy, A., Toderici, G., Shetty, S., Leung , T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Columbus, OH, USA (2014). https://doi.org/10.1109/CVPR.2014.223
Lopes, U.K., Valiati, J.F.: Pre-trained convolutional neural networks as feature extractors for tuberculosis detection in biology and medicine 89, 135–143 (2017). https://doi.org/10.1016/j.compbiomed.2017.08.001
Lopez, Y. P., Filho, C. F. F C., Aguilera, L. M. R., Costa, M. G. F.: Automatic classification of light field smear microscopy patches using Convolutional Neural Networks for identifying Mycobacterium Tuberculosis. In: CHILECON. IEEE, Pucon Chile (2017). https://doi.org/10.1109/CHILECON.2017.8229512
Marcelino, P.: Transfer learning from pre-trained models. http://towardsdatascience.com/transfer-learning-from-pre-trained-models-f2393f124751
Molicotti, P., Bua, A., Zanetti, S.: Cost-effectiveness in the diagnosis of tuberculosis: choices in developing countries. J. Infect. Dev. Countries 8(01), 024–038 (2014). https://doi.org/10.3855/jidc.3295
Mwesigwa, A.: Uganda crippled by medical brain drain. http://www.theguardian.com/global-development/2015/feb/10/Uganda-crippled-medical-brain-drain-doctors
Özgenel, Ç. F., Sorguç, A.G.: Performance comparison of pretrained convolutional neural networks on crack detection in buildings. In: 35th International Symposium on Automation and Robotics in Construction (ISARC) (2018). https://doi.org/10.22260/ISARC2018/0094
Panicker, R.O., Kalmady, K.S., Rajan, J., Sabu, M.K.: Automatic detection of tuberculosis bacilli from microscopic sputum images using deep learning methods. Biocybern. Biomed. Eng. 38, 691–699 (2018). https://doi.org/10.1016/j.bbe.2018.05
Quinn, J.A., Nakasi, R., Mugagga, P.K.B., Byanyima, P., Lubega, W., Andama, A.: Deep convolutional neural networks for microscopy-based point of care diagnostics. In: Machine Learning for Healthcare Conference, pp. 271-281. Los Angeles, California (2016)
Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: CVPR 2014 Deep Vision Workshop, pp. 512–519. IEEE, Columbus, OH, USA (2014). https://doi.org/10.1109/CVPRW.2014.131
Surgitha, G.E., Murugesan, G.: Detection of tuberculosis bacilli from microscopic sputum smear images. In: ICBSII. IEEE Press, Chennai, India (2017). https://doi.org/10.1109/ICBSII.2017.8082271
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Press, Boston (2015). https://doi.org/10.1109/CVPR.2015.7298594
Szegedy, C., Vanhoucke, V., Ioffe S., Shlens, J.,Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Press, Las Vegas (2016). https://doi.org/10.1109/CVPR.2016.308
Transfer Learning Using Pretrained ConvNets. http://www.tensorflow.org/tutorials/images/transferlearning
Visual Geometry Group. http://www.robots.ox.ac.uk/vgg/research/verydeep/
World Health Organization: World Health Organization Global Tuberculosis Report 2017. World Health Organization, Geneva, Switzerland. https://www.who.int/tb/publications/global_report/gtbr2017_main_text.pdf
Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: a decade survey of instance retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1224–44 (2017)
ZNSM iDB: Ziehl Neelsen Sputum Smear Microscopy Image Database. https://14.139.240.55/znsm/
Acknowledgments
This work was supported by the SIDA project 381 under the Makerere-Swedish bilateral research programme 2015–2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Muyama, L., Nakatumba-Nabende, J., Mudali, D. (2021). Automated Detection of Tuberculosis from Sputum Smear Microscopic Images Using Transfer Learning Techniques. In: Abraham, A., Siarry, P., Ma, K., Kaklauskas, A. (eds) Intelligent Systems Design and Applications. ISDA 2019. Advances in Intelligent Systems and Computing, vol 1181. Springer, Cham. https://doi.org/10.1007/978-3-030-49342-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-49342-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-49341-7
Online ISBN: 978-3-030-49342-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)