TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model

V. Shwetha

doi:10.1007/978-981-99-3758-5_8

TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model

V. Shwetha^*

^*Corresponding author for this work

Manipal Institute of Technology, Manipal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Manual evaluation of TB bacteria from Ziehl-Neelsen images is a tedious process. Computer Aided Diagnosis for image analysis helps increase the throughput. In Ziehl-Neelsen sputum smear images, bacilli appear very small and often overlap with WBC. This results in a setback in the automation process. Recent advances in CNNs in solving medical image-related diagnosis help in faster diagnosis. The present study is focused on the application of an object detection model in TB bacteria detection process. The study showed that the RetinaNet-based object detection model is suitable for microscopic ZN images resulting in an Average Precision of 0. 91 for WBC and 0.94 for bacilli bacteria.

Original language	English
Title of host publication	ICT with Intelligent Applications - ICTIS 2023
Editors	Jyoti Choudrie, Parikshit N. Mahalle, Thinagaran Perumal, Amit Joshi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	77-85
Number of pages	9
ISBN (Print)	9789819937578
DOIs	https://doi.org/10.1007/978-981-99-3758-5_8
Publication status	Published - 2023
Event	7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023 - Ahmedabad, India Duration: 27-04-2023 → 28-04-2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	719 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023
Country/Territory	India
City	Ahmedabad
Period	27-04-23 → 28-04-23

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-981-99-3758-5_8

Cite this

Shwetha, V. (2023). TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model. In J. Choudrie, P. N. Mahalle, T. Perumal, & A. Joshi (Eds.), ICT with Intelligent Applications - ICTIS 2023 (pp. 77-85). (Lecture Notes in Networks and Systems; Vol. 719 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-3758-5_8

@inproceedings{0c55ea1ad68246dca3e9581d64806ff8,

title = "TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model",

abstract = "Manual evaluation of TB bacteria from Ziehl-Neelsen images is a tedious process. Computer Aided Diagnosis for image analysis helps increase the throughput. In Ziehl-Neelsen sputum smear images, bacilli appear very small and often overlap with WBC. This results in a setback in the automation process. Recent advances in CNNs in solving medical image-related diagnosis help in faster diagnosis. The present study is focused on the application of an object detection model in TB bacteria detection process. The study showed that the RetinaNet-based object detection model is suitable for microscopic ZN images resulting in an Average Precision of 0. 91 for WBC and 0.94 for bacilli bacteria.",

author = "V. Shwetha",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023 ; Conference date: 27-04-2023 Through 28-04-2023",

year = "2023",

doi = "10.1007/978-981-99-3758-5\_8",

language = "English",

isbn = "9789819937578",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "77--85",

editor = "Jyoti Choudrie and Mahalle, \{Parikshit N.\} and Thinagaran Perumal and Amit Joshi",

booktitle = "ICT with Intelligent Applications - ICTIS 2023",

address = "Germany",

}

Shwetha, V 2023, TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model. in J Choudrie, PN Mahalle, T Perumal & A Joshi (eds), ICT with Intelligent Applications - ICTIS 2023. Lecture Notes in Networks and Systems, vol. 719 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 77-85, 7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023, Ahmedabad, India, 27-04-23. https://doi.org/10.1007/978-981-99-3758-5_8

TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model. / Shwetha, V.
ICT with Intelligent Applications - ICTIS 2023. ed. / Jyoti Choudrie; Parikshit N. Mahalle; Thinagaran Perumal; Amit Joshi. Springer Science and Business Media Deutschland GmbH, 2023. p. 77-85 (Lecture Notes in Networks and Systems; Vol. 719 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - TB Bacteria and WBC Detection from ZN-Stained Sputum Smear Images Using Object Detection Model

AU - Shwetha, V.

PY - 2023

Y1 - 2023

N2 - Manual evaluation of TB bacteria from Ziehl-Neelsen images is a tedious process. Computer Aided Diagnosis for image analysis helps increase the throughput. In Ziehl-Neelsen sputum smear images, bacilli appear very small and often overlap with WBC. This results in a setback in the automation process. Recent advances in CNNs in solving medical image-related diagnosis help in faster diagnosis. The present study is focused on the application of an object detection model in TB bacteria detection process. The study showed that the RetinaNet-based object detection model is suitable for microscopic ZN images resulting in an Average Precision of 0. 91 for WBC and 0.94 for bacilli bacteria.

AB - Manual evaluation of TB bacteria from Ziehl-Neelsen images is a tedious process. Computer Aided Diagnosis for image analysis helps increase the throughput. In Ziehl-Neelsen sputum smear images, bacilli appear very small and often overlap with WBC. This results in a setback in the automation process. Recent advances in CNNs in solving medical image-related diagnosis help in faster diagnosis. The present study is focused on the application of an object detection model in TB bacteria detection process. The study showed that the RetinaNet-based object detection model is suitable for microscopic ZN images resulting in an Average Precision of 0. 91 for WBC and 0.94 for bacilli bacteria.

UR - https://www.scopus.com/pages/publications/85174726232

UR - https://www.scopus.com/pages/publications/85174726232#tab=citedBy

U2 - 10.1007/978-981-99-3758-5_8

DO - 10.1007/978-981-99-3758-5_8

M3 - Conference contribution

AN - SCOPUS:85174726232

SN - 9789819937578

T3 - Lecture Notes in Networks and Systems

SP - 77

EP - 85

BT - ICT with Intelligent Applications - ICTIS 2023

A2 - Choudrie, Jyoti

A2 - Mahalle, Parikshit N.

A2 - Perumal, Thinagaran

A2 - Joshi, Amit

PB - Springer Science and Business Media Deutschland GmbH

T2 - 7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023

Y2 - 27 April 2023 through 28 April 2023

ER -