MULTICLASS SEGMENTATION OF 3D MEDICAL DATA WITH DEEP LEARNING

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU136707" target="_blank" >RIV/00216305:26220/20:PU136707 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2020_sbornik_1.pdf" target="_blank" >https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2020_sbornik_1.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

MULTICLASS SEGMENTATION OF 3D MEDICAL DATA WITH DEEP LEARNING

Popis výsledku v původním jazyce

This paper deals with multiclass image segmentation using convolutional neural networks. The theoretical part of paper focuses on image segmentation. There are basics principles of neural networks and image segmentation with more types of approaches. In practical part the Unet architecture is chosen and is described for image segmentation more. U-net was applied for medicine dataset which consist from 3D MRI of human brain. There is processing procedure which is more described for image processing of three-dimensional data. There are also methods for data preprocessing which were applied for image multiclass segmentation. Final part of paper evaluates results which were achieved with chosen method.

Název v anglickém jazyce

MULTICLASS SEGMENTATION OF 3D MEDICAL DATA WITH DEEP LEARNING

Popis výsledku anglicky

This paper deals with multiclass image segmentation using convolutional neural networks. The theoretical part of paper focuses on image segmentation. There are basics principles of neural networks and image segmentation with more types of approaches. In practical part the Unet architecture is chosen and is described for image segmentation more. U-net was applied for medicine dataset which consist from 3D MRI of human brain. There is processing procedure which is more described for image processing of three-dimensional data. There are also methods for data preprocessing which were applied for image multiclass segmentation. Final part of paper evaluates results which were achieved with chosen method.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů