TY - GEN
T1 - Adversarial Learning Based Semi-supervised Semantic Segmentation of Low Resolution Gram Stained Microscopic Images
AU - Singh, Harshal
AU - Kanabur, Vidyashree R.
AU - Sumam, S. David
AU - Vijayasenan, Deepu
AU - Govindan, Sreejith
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Urinary tract infections (UTIs) are infections that affect the urinary system. It is usually caused by bacteria and pus cells. Analyzing urine samples, including examining pus cells, is a standard method for diagnosing and monitoring UTIs. However, manually detecting bacteria or pus cells in microscopic urine images is a time-consuming and labour-intensive task for microbiologists. Therefore, the segmentation of microscopic pus cell images will ease the process of detecting UTI. Especially low resolution microscopic images are hard to annotate; therefore, in this study, we propose an adversarial learning based semi-supervised segmentation method for segmentation of pus cell images at low resolution i.e. 40× using labeled high resolution images i.e. 100×. The proposed methodology aims to ease the process of UTI detection by automating the segmentation of pus cell images. The results of the proposed methodology demonstrate an increase in the Dice coefficient score percentage by 1%, 1.6% and 2.4% on 40× images when compared to fully supervised segmentation model trained on only 100× data using three different architectures- Unet, ResUnet++, and PSPnet, respectively.
AB - Urinary tract infections (UTIs) are infections that affect the urinary system. It is usually caused by bacteria and pus cells. Analyzing urine samples, including examining pus cells, is a standard method for diagnosing and monitoring UTIs. However, manually detecting bacteria or pus cells in microscopic urine images is a time-consuming and labour-intensive task for microbiologists. Therefore, the segmentation of microscopic pus cell images will ease the process of detecting UTI. Especially low resolution microscopic images are hard to annotate; therefore, in this study, we propose an adversarial learning based semi-supervised segmentation method for segmentation of pus cell images at low resolution i.e. 40× using labeled high resolution images i.e. 100×. The proposed methodology aims to ease the process of UTI detection by automating the segmentation of pus cell images. The results of the proposed methodology demonstrate an increase in the Dice coefficient score percentage by 1%, 1.6% and 2.4% on 40× images when compared to fully supervised segmentation model trained on only 100× data using three different architectures- Unet, ResUnet++, and PSPnet, respectively.
UR - https://www.scopus.com/pages/publications/85200657282
UR - https://www.scopus.com/pages/publications/85200657282#tab=citedBy
U2 - 10.1007/978-3-031-58174-8_31
DO - 10.1007/978-3-031-58174-8_31
M3 - Conference contribution
AN - SCOPUS:85200657282
SN - 9783031581731
T3 - Communications in Computer and Information Science
SP - 362
EP - 373
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 -