An overview of abdominal segmentation methods using General Adversarial Network (GAN)

Ying Liu

doi:10.1117/12.2660662

6 December 2022 An overview of abdominal segmentation methods using General Adversarial Network (GAN)

Ying Liu

Proceedings Volume 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022); 1245843 (2022) https://doi.org/10.1117/12.2660662
Event: International Conference on Biomedical and Intelligent Systems, 2022, Chengdu, China

Abstract

Applications ranging from image-guided surgery to computer-assisted diagnosis depend on the segmentation of abdominal anatomy. The uses of the General Adversarial Network (GAN) in the automatic segmentation of abdominal pictures are discussed in this review article. Discussion in this paper starts off by reviewing the underlying theory of GAN and its variations, then covering the most recent abdominal segmentation techniques. In addition, it introduces the variety of applications and datasets included for these imaging studies. The quantitative performances (evaluated using Dice Similarity Coefficient and F-scores) of 13 representative studies are summarized and compared. Overall, a more precise abdominal segmentation can be achieved using GAN-based methods of image analysis.

Citation Download Citation

Ying Liu "An overview of abdominal segmentation methods using General Adversarial Network (GAN)", Proc. SPIE 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022), 1245843 (6 December 2022); https://doi.org/10.1117/12.2660662

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