Cell image segmentation method based on U2-Net

Pinchen Zhu; Bingrui Shi; Zichun Xie; Jiale Hu; Jianhui Zhan; Yihong Huang; Yu Zheng

doi:10.1117/12.2639702

19 October 2022 Cell image segmentation method based on U2-Net

Pinchen Zhu, Bingrui Shi, Zichun Xie, Jiale Hu, Jianhui Zhan, Yihong Huang, Yu Zheng

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122944P (2022) https://doi.org/10.1117/12.2639702
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

Cell segmentation is an important direction in biological and medical image processing. As a new image segmentation method, U2-Net not only has a better segmentation effect, but also has a better segmentation effect on adherent cells than traditional cell segmentation methods. This paper presents a U2-Net based cell segmentation method, analyses the structure and innovation of the algorithm, puts forward an effective execution process, trains and measures the results through pixel accuracy and loss function, selects the optimal model for cell image segmentation. After experiments, the effect of cell division is remarkable, and representative results of cell division are obtained.

Citation Download Citation

Pinchen Zhu, Bingrui Shi, Zichun Xie, Jiale Hu, Jianhui Zhan, Yihong Huang, and Yu Zheng "Cell image segmentation method based on U2-Net", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122944P (19 October 2022); https://doi.org/10.1117/12.2639702

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available