CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12179 > Article
Paper
10 June 2022 Automatic liver tumor segmentation based on modified V-Net from multi-phase CT images
Yanfeng Wang, Hongye Ban, Panlong Li, Zhou Zhou, Haihao Du
Author Affiliations +
Proceedings Volume 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022); 1217904 (2022) https://doi.org/10.1117/12.2636500
Event: Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 2022, Xiamen, China
Abstract
Liver cancer segmentation is an important process for doctors to diagnose liver tumors and the patient's subsequent treatments. Computed tomography (CT) scan images are often used because of their high spatial resolution, clear image and speediness. However, most of existing liver tumor segmentation algorithms perform feature extraction from singlephase CT images, ignoring the rich supplementary information provided by multi-phase CT images. Therefore, combined with the attention mechanism, we proposed a multi-channel attention gate V-Net (MCAGV-Net) based on the attention gate module for the automatic liver tumor segmentation by fusing multi-phase CT images information. The algorithm was verified by a multi-phase CT dataset. To further illustrate the performance of this algorithm, accuracy of segmentation by our algorithm was compared with previous algorithm. For liver segmentation, the Dice score is 90.46%, which was 3.92% higher than the single-channel V-Net. For liver tumor segmentation, the Dice score is 69.65%, which was increased 2.41% compared with the single-channel V-Net. In this work, we show that MCAGV-Net can effectively solve the problem of liver tumor segmentation, and for single-channel networks, the accuracy has also been improved.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yanfeng Wang, Hongye Ban, Panlong Li, Zhou Zhou, and Haihao Du "Automatic liver tumor segmentation based on modified V-Net from multi-phase CT images", Proc. SPIE 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 1217904 (10 June 2022); https://doi.org/10.1117/12.2636500
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 8 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation
Liver
Computed tomography
3D image processing
Image processing
Image fusion
Liver cancer
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top