On Improving 3D U-net Architecture
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332644" target="_blank" >RIV/68407700:21230/19:00332644 - isvavai.cz</a>
Result on the web
<a href="https://www.scitepress.org/PublicationsDetail.aspx?ID=ZmJ8fAjUpDc%3d&t=1" target="_blank" >https://www.scitepress.org/PublicationsDetail.aspx?ID=ZmJ8fAjUpDc%3d&t=1</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5220/0007830306490656" target="_blank" >10.5220/0007830306490656</a>
Alternative languages
Result language
angličtina
Original language name
On Improving 3D U-net Architecture
Original language description
This paper presents a review of various techniques for improving the performance of neural networks on segmentation task using 3D convolutions and voxel grids – we provide comparison of network with and without max pooling, weighting, masking out the segmentation results, and oversampling results for imbalanced training dataset. We also present changes to 3D U-net architecture that give better results than the standard implementation. Although there are many out-performing architectures using different data input, we show, that although the voxel grids that serve as an input to the 3D U-net, have limits to what they can express, they do not reach their full potential.
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
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
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 of the 14th International Conference on Software Technologies
ISBN
978-989-758-379-7
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
649-656
Publisher name
SciTePress - Science and Technology Publications
Place of publication
Porto
Event location
Praha
Event date
Jul 26, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—