A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data

Vidyashree R. Kanabur; Deepu Vijayasenan; Sumam David S; Sreejith Govindan

doi:10.1007/978-3-031-58181-6_21

A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data

Vidyashree R. Kanabur^*
, Deepu Vijayasenan
, Sumam David S
, Sreejith Govindan

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Urine smear analysis aids in preliminary diagnosis of Urinary Tract Infection. But it is time-consuming and requires a lot of medical expertise. Automating the process using machine learning can save time and effort. However obtaining a large medical dataset is difficult due to data privacy concerns and medical expertise requirements. In this study, we propose a method to synthesize a large dataset of gram-stained microscopic images containing pus cells and bacteria. We train a machine learning model to achieve semantic segmentation of bacteria and pus cells using this dataset. Later we use it to perform transfer learning on a relatively small dataset of gram stained urine microscopic images. Our approach improved the F1-score from 50% to 63% for bacteria segmentation and from 77% to 83% for pus cell segmentation. This method has the potential to improve the turn-around time and the quality of preliminary diagnosis of Urinary Tract Infection.

Original language	English
Title of host publication	Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers
Editors	Harkeerat Kaur, Vinit Jakhetiya, Puneet Goyal, Pritee Khanna, Balasubramanian Raman, Sanjeev Kumar
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	244-255
Number of pages	12
ISBN (Print)	9783031581809
DOIs	https://doi.org/10.1007/978-3-031-58181-6_21
Publication status	Published - 2024
Event	8th International Conference on Computer Vision and Image Processing, CVIP 2023 - Jammu, India Duration: 03-11-2023 → 05-11-2023

Publication series

Name	Communications in Computer and Information Science
Volume	2009 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	8th International Conference on Computer Vision and Image Processing, CVIP 2023
Country/Territory	India
City	Jammu
Period	03-11-23 → 05-11-23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

All Science Journal Classification (ASJC) codes

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-031-58181-6_21

Cite this

Kanabur, V. R., Vijayasenan, D., S, S. D., & Govindan, S. (2024). A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data. In H. Kaur, V. Jakhetiya, P. Goyal, P. Khanna, B. Raman, & S. Kumar (Eds.), Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers (pp. 244-255). (Communications in Computer and Information Science; Vol. 2009 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-58181-6_21

Kanabur, Vidyashree R. ; Vijayasenan, Deepu ; S, Sumam David et al. / A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data. Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers. editor / Harkeerat Kaur ; Vinit Jakhetiya ; Puneet Goyal ; Pritee Khanna ; Balasubramanian Raman ; Sanjeev Kumar. Springer Science and Business Media Deutschland GmbH, 2024. pp. 244-255 (Communications in Computer and Information Science).

@inproceedings{52258d96c08e4a548e37443e7f1ba952,

title = "A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data",

abstract = "Urine smear analysis aids in preliminary diagnosis of Urinary Tract Infection. But it is time-consuming and requires a lot of medical expertise. Automating the process using machine learning can save time and effort. However obtaining a large medical dataset is difficult due to data privacy concerns and medical expertise requirements. In this study, we propose a method to synthesize a large dataset of gram-stained microscopic images containing pus cells and bacteria. We train a machine learning model to achieve semantic segmentation of bacteria and pus cells using this dataset. Later we use it to perform transfer learning on a relatively small dataset of gram stained urine microscopic images. Our approach improved the F1-score from 50\% to 63\% for bacteria segmentation and from 77\% to 83\% for pus cell segmentation. This method has the potential to improve the turn-around time and the quality of preliminary diagnosis of Urinary Tract Infection.",

author = "Kanabur, \{Vidyashree R.\} and Deepu Vijayasenan and S, \{Sumam David\} and Sreejith Govindan",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 8th International Conference on Computer Vision and Image Processing, CVIP 2023 ; Conference date: 03-11-2023 Through 05-11-2023",

year = "2024",

doi = "10.1007/978-3-031-58181-6\_21",

language = "English",

isbn = "9783031581809",

series = "Communications in Computer and Information Science",

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

pages = "244--255",

editor = "Harkeerat Kaur and Vinit Jakhetiya and Puneet Goyal and Pritee Khanna and Balasubramanian Raman and Sanjeev Kumar",

booktitle = "Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers",

address = "Germany",

}

Kanabur, VR, Vijayasenan, D, S, SD & Govindan, S 2024, A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data. in H Kaur, V Jakhetiya, P Goyal, P Khanna, B Raman & S Kumar (eds), Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers. Communications in Computer and Information Science, vol. 2009 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 244-255, 8th International Conference on Computer Vision and Image Processing, CVIP 2023, Jammu, India, 03-11-23. https://doi.org/10.1007/978-3-031-58181-6_21

A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data. / Kanabur, Vidyashree R.; Vijayasenan, Deepu; S, Sumam David et al.
Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers. ed. / Harkeerat Kaur; Vinit Jakhetiya; Puneet Goyal; Pritee Khanna; Balasubramanian Raman; Sanjeev Kumar. Springer Science and Business Media Deutschland GmbH, 2024. p. 244-255 (Communications in Computer and Information Science; Vol. 2009 CCIS).

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

TY - GEN

T1 - A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data

AU - Kanabur, Vidyashree R.

AU - Vijayasenan, Deepu

AU - S, Sumam David

AU - Govindan, Sreejith

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - Urine smear analysis aids in preliminary diagnosis of Urinary Tract Infection. But it is time-consuming and requires a lot of medical expertise. Automating the process using machine learning can save time and effort. However obtaining a large medical dataset is difficult due to data privacy concerns and medical expertise requirements. In this study, we propose a method to synthesize a large dataset of gram-stained microscopic images containing pus cells and bacteria. We train a machine learning model to achieve semantic segmentation of bacteria and pus cells using this dataset. Later we use it to perform transfer learning on a relatively small dataset of gram stained urine microscopic images. Our approach improved the F1-score from 50% to 63% for bacteria segmentation and from 77% to 83% for pus cell segmentation. This method has the potential to improve the turn-around time and the quality of preliminary diagnosis of Urinary Tract Infection.

AB - Urine smear analysis aids in preliminary diagnosis of Urinary Tract Infection. But it is time-consuming and requires a lot of medical expertise. Automating the process using machine learning can save time and effort. However obtaining a large medical dataset is difficult due to data privacy concerns and medical expertise requirements. In this study, we propose a method to synthesize a large dataset of gram-stained microscopic images containing pus cells and bacteria. We train a machine learning model to achieve semantic segmentation of bacteria and pus cells using this dataset. Later we use it to perform transfer learning on a relatively small dataset of gram stained urine microscopic images. Our approach improved the F1-score from 50% to 63% for bacteria segmentation and from 77% to 83% for pus cell segmentation. This method has the potential to improve the turn-around time and the quality of preliminary diagnosis of Urinary Tract Infection.

UR - https://www.scopus.com/pages/publications/85200326812

UR - https://www.scopus.com/pages/publications/85200326812#tab=citedBy

U2 - 10.1007/978-3-031-58181-6_21

DO - 10.1007/978-3-031-58181-6_21

M3 - Conference contribution

AN - SCOPUS:85200326812

SN - 9783031581809

T3 - Communications in Computer and Information Science

SP - 244

EP - 255

BT - Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers

A2 - Kaur, Harkeerat

A2 - Jakhetiya, Vinit

A2 - Goyal, Puneet

A2 - Khanna, Pritee

A2 - Raman, Balasubramanian

A2 - Kumar, Sanjeev

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th International Conference on Computer Vision and Image Processing, CVIP 2023

Y2 - 3 November 2023 through 5 November 2023

ER -

Kanabur VR, Vijayasenan D, S SD, Govindan S. A Deep Learning Approach to Enhance Semantic Segmentation of Bacteria and Pus Cells from Microscopic Urine Smear Images Using Synthetic Data. In Kaur H, Jakhetiya V, Goyal P, Khanna P, Raman B, Kumar S, editors, Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2024. p. 244-255. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-58181-6_21