Sub-region segmentation of brain tumors from multimodal MRI images using 3D U-Net
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F23%3A63570398" target="_blank" >RIV/70883521:28140/23:63570398 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-21438-7_29" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-21438-7_29</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-21438-7_29" target="_blank" >10.1007/978-3-031-21438-7_29</a>
Alternative languages
Result language
angličtina
Original language name
Sub-region segmentation of brain tumors from multimodal MRI images using 3D U-Net
Original language description
Accurate segmentation of brain tumors from the magnetic resonance image (MRI) is an essential step for radionics analysis as well as finding the tumor extension is so necessary to plan the best treatment to improve the survival rate. Manually extracting sub-regions of the brain tumor from MRI is a tedious process and time-consuming, as the complex brain tumor images require extensive human expertise. In recent years, deep learning models have proved effective in medical image segmentation tasks. In brain tumor segmentation, the 3D multimodal MRI poses some challenges such as computation and memory limitations. This study aims to develop a deep learning model using 3D U-Net for brain tumor segmentation. The segmentation results on BraTS 2020 dataset show that the proposed model achieves promising performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lecture Notes in Networks and System (Volume 597 LNNS)
ISBN
978-3-031-21437-0
ISSN
2367-3370
e-ISSN
—
Number of pages
11
Pages from-to
357-367
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
Berlín
Event location
on-line
Event date
Oct 10, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000992418500029