Segmentation of liver CT images based on the improved UNet network

Xiangyu Deng; Yangyang Bian; Yao Ma

doi:10.1117/12.2661313

16 December 2022 Segmentation of liver CT images based on the improved UNet network

Xiangyu Deng, Yangyang Bian, Yao Ma

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125003R (2022) https://doi.org/10.1117/12.2661313
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

In clinical medicine, the liver segmentation is indispensable for the diagnosis of liver diseases. The shape and size of the liver varies in CT images and the similar grayscale values with neighboring organ tissues, which cause difficulties for segmentation. For these problems, we propose a network for the segmentation of liver CT images, which based on encoder-decoder structure. The network applies the SE-Res block instead of the original convolution block to optimize the boundary information and apply the spatial-channel attention gate to enhance the features of the liver in the decoder. The proposed algorithm was validated on the LITS-28 dataset, the Mean Intersection over Union (MIOU) and Dice similarity coefficient (Dice) were 93.68% and 96.45%, respectively. Compared with other similar algorithms, the performance of the proposed algorithm is better and the segmented liver results are more accurate.

Citation Download Citation

Xiangyu Deng, Yangyang Bian, and Yao Ma "Segmentation of liver CT images based on the improved UNet network", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125003R (16 December 2022); https://doi.org/10.1117/12.2661313

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image segmentation

Liver

Computed tomography

Computer programming

Image processing algorithms and systems

Convolution

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years