Abstract
Nowadays, tuberculosis is one of the more deadly diseases. Nevertheless, an accurate and fast diagnosis has a great influence on disease prognosis. The research goal of this work is to speed up the time to diagnosis, as well as to improve the sensibility of sputum microscopy as a tuberculosis diagnosis tool. This work presents a novel deep learning technique for automatic bacilli detection in Ziehl Neelsen (ZN) stain sputum microscopy. First, the microscopy images are enhanced and completely fragmented. Then a single deep convolutional network indicates which image fragments include bacilli or not. Results demonstrate the effectiveness of our framework, obtaining a 92.86% recall and 99.49% precision, along with a significantly decreasing detection time. Finally, this research compared the results with previous works in bacilli detection, showing a considerable improvement in the results, illustrating the feasibility of our results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
World Health Organization (WHO) (2022). Global Tuberculosis Report 2022. https://www.who.int/publications/i/item/9789240061729
Das, P.K., Ganguly, S.B., Mandal, B.: Sputum smear microscopy in tuberculosis: it is still relevant in the era of molecular diagnosis when seen from the public health perspective. Biomed. Biotechnol. Res. J. (BBRJ) 3(2), 77 (2019)
Deka, B.C., Saikia, D., Pratim Kashyap, M.: Diagnosis of tuberculosis. Europ. Jo. Molecular Clin.Med. 9(07) (2022)
Global Laboratory Initiative (GLI). Laboratory Diagnosis of Tuberculosis by Sputum Microscopy (2013)
Raof, R.A.A., Mashor, M.Y., Ahmad, R.B., Noor, S.S.M.: Image segmentation of Ziehl-Neelsen sputum slide images for tubercle Bacilli detection. Image Segmentation, pp. 365–378 (2011)
Li, Z., Ling, J., Wu, J., Luo, N., Tan, M., Zhong, P.: Research on preprocessing method for microscopic image of sputum smear and intelligent counting for Tubercule Bacillus. IOP Conf. Ser. Mater. Sci. Eng. 466(1), 012112 (2018). IOP Publishing (2018)
Panicker, R.O., Kalmady, K.S., Rajan, J., Sabu, M.K.: Automatic detection of tuberculosis bacilli from microscopic sputum smear images using deep learning methods. Biocybern. Biomed. Eng. 38(3), 691–699 (2018)
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 (2018)
El-Melegy, M., Mohamed, D., ElMelegy, T.: Automatic detection of tuberculosis Bacilli from microscopic sputum smear images using faster R-CNN, transfer learning and augmentation. In: Morales, A., Fierrez, J., Sánchez, J.S., Ribeiro, B. (eds.) IbPRIA 2019. LNCS, vol. 11867, pp. 270–278. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-31332-6_24
Shwetha, V., Prasad, K., Mukhopadhyay, C., Banerjee, B., Chakrabarti, A.: Automatic detection of Bacilli bacteria from Ziehl-Neelsen sputum smear images. In: 2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4), pp. 1–5. IEEE (2021)
Mithra, K.S., Sam Emmanuel, W.R.: Automated identification of mycobacterium bacillus from sputum images for tuberculosis diagnosis. SIViP 13(8), 1585–1592 (2019). https://doi.org/10.1007/s11760-019-01509-1
Panicker, R. O., Soman, B., Sabu, M.K.: Tuberculosis detection from conventional sputum smear microscopic images using machine learning techniques. In: Hybrid Computational Intelligence, pp. 63–80. CRC Press (2019)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
Uddin, S.: Tuberculosis Image Dataset. https://www.kaggle.com/datasets/saife245/tuberculosis-image-datasets. Accessed March 2023
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211-252 (2015)
Acknowledgments
This work was supported by the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No 853989. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA and Global Alliance for TB Drug Development non-profit organisation, Bill & Melinda Gates Foundation and University of Dundee.
DISCLAIMER. This work reflects only the author’s views, and the JU is not responsible for any use that may be made of the information it contains.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Visuña, L., Garcia-Blas, J., Carretero, J. (2023). Novel Deep Learning-Based Technique for Tuberculosis Bacilli Detection in Sputum Microscopy. In: Daimi, K., Al Sadoon, A. (eds) Proceedings of the Second International Conference on Innovations in Computing Research (ICR’23). Lecture Notes in Networks and Systems, vol 721. Springer, Cham. https://doi.org/10.1007/978-3-031-35308-6_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-35308-6_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35307-9
Online ISBN: 978-3-031-35308-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)