Brain tumor segmentation with parallel convolutional neural networks

Fang Li

doi:10.1117/12.2635429

6 May 2022 Brain tumor segmentation with parallel convolutional neural networks

Fang Li

Proceedings Volume 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022); 122560B (2022) https://doi.org/10.1117/12.2635429
Event: 2022 International Conference on Electronic Information Engineering, Big Data and Computer Technology, 2022, Sanya, China

Abstract

To solve the problems existing in the traditional networks, we have improved the existing networks. Traditional networks mainly focus on the details of images and ignore the importance of global features in the segmentation. In addition, the increasing depth of the network leads to a series of problems, such as over-fitting, decreasing convergence, drop-in speed and decreasing accuracy. Moreover, convolving with unified scale in the same layer fails in comprehensively representing the feature information. To address the above problems, a combination of deep network and corresponding shallow network is proposed to extract the image features for segmentation. In order to speed up training, a shortcut connection is employed in cascade with small kernels to facilitate gradient flow. Besides, we add a multi-scale operation to the network for extracting the both short-range and long-range contextual information. Our proposals are validated in the BRATS2013 database, obtaining the excellent performance in the Complete and Core of Dice and Sensitivity (0.89, 0.81, 0.89, 0.78) simultaneously for the Training data set.

Citation Download Citation

Fang Li "Brain tumor segmentation with parallel convolutional neural networks", Proc. SPIE 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022), 122560B (6 May 2022); https://doi.org/10.1117/12.2635429

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Tumors

Image segmentation

Brain

Convolution

Convolutional neural networks

Feature extraction

Image processing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years