TY - GEN
T1 - YOLO Based Segmentation and CNN Based Classification Framework for Epithelial and Pus Cell Detection
AU - Shwetha, V.
AU - Prasad, Keerthana
AU - Mukhopadhyay, Chiranjay
AU - banerjee, Barnini
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Identifying the cells, such as pus and epithelial cells, from microscopic images is one of the important steps in medical diagnostics. Microscopic examination by hand is labor-intensive and unreliable. Therefore, it is helpful to have an automated approach for classifying these cells to enable quick and accurate diagnosis. Creating a model for automated cell identification is challenging because of the numerous variable parameters such as various stains and magnifications and cell overlapping. This paper offers a robust object detection model that detects the pus and epithelial cells images obtained from the microscopic analysis of direct samples of Gram-stained patient samples such as pus and sputum. This paper also presents a novel classifier that addresses the overlapping issues present in the cells. The proposed methodology offers an mAP of 0.87 and a classification accuracy of 94.5%.
AB - Identifying the cells, such as pus and epithelial cells, from microscopic images is one of the important steps in medical diagnostics. Microscopic examination by hand is labor-intensive and unreliable. Therefore, it is helpful to have an automated approach for classifying these cells to enable quick and accurate diagnosis. Creating a model for automated cell identification is challenging because of the numerous variable parameters such as various stains and magnifications and cell overlapping. This paper offers a robust object detection model that detects the pus and epithelial cells images obtained from the microscopic analysis of direct samples of Gram-stained patient samples such as pus and sputum. This paper also presents a novel classifier that addresses the overlapping issues present in the cells. The proposed methodology offers an mAP of 0.87 and a classification accuracy of 94.5%.
UR - http://www.scopus.com/inward/record.url?scp=85172272501&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85172272501&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-37940-6_38
DO - 10.1007/978-3-031-37940-6_38
M3 - Conference contribution
AN - SCOPUS:85172272501
SN - 9783031379390
T3 - Communications in Computer and Information Science
SP - 466
EP - 477
BT - Advances in Computing and Data Sciences - 7th International Conference, ICACDS 2023, Revised Selected Papers
A2 - Singh, Mayank
A2 - Tyagi, Vipin
A2 - Gupta, P.K.
A2 - Flusser, Jan
A2 - Ören, Tuncer
PB - Springer Science and Business Media Deutschland GmbH
T2 - Proceedings of the 7th International Conference on Advances in Computing and Data Sciences, ICACDS 2023
Y2 - 27 April 2023 through 28 April 2023
ER -