Implementation of a deep learning model for vertebral segmentation in CT data
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F23%3APU148717" target="_blank" >RIV/00216305:26220/23:PU148717 - isvavai.cz</a>
Result on the web
<a href="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf" target="_blank" >https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.13164/eeict.2023.41" target="_blank" >10.13164/eeict.2023.41</a>
Alternative languages
Result language
angličtina
Original language name
Implementation of a deep learning model for vertebral segmentation in CT data
Original language description
This paper deals with the problem of vertebral segmentation in CT data with the use of deep learning approaches. Automatic segmentation of vertebrae is a very complex issue and would simplify the work of radiologists and doctors. The paper is focused on one of the models published and submitted to the Large Scale Vertebrae Segmentation Challenge (VerSe) in 2020 from C. Payer et al. – Improving Coarse to Fine Vertebrae Localisation and Segmentation with SpatialConfiguration-Net and U-Net and its implementation and modification. The model is evaluated on the corresponding public and hidden dataset. Its modification shows an improvement of the results in comparison with the published results, a mean Dice score improved from 0.9165 to 0.9302 on the public dataset and from 0.8971 to 0.9264 on the hidden dataset.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20601 - Medical engineering
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
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
Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected papers
ISBN
978-80-214-6154-3
ISSN
2788-1334
e-ISSN
—
Number of pages
4
Pages from-to
41-44
Publisher name
Brno University of Technology, Faculty of Electrical Engineering and Communication
Place of publication
Brno, Czech Republic
Event location
Brno
Event date
Apr 25, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—