Brain Tumour Diagnostics Support Based on Medical Image Segmentation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60461373%3A22340%2F09%3A00022069" target="_blank" >RIV/60461373:22340/09:00022069 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Brain Tumour Diagnostics Support Based on Medical Image Segmentation

Popis výsledku v původním jazyce

High-grade gliomas represent rapidly growing malignant brain tumours. Early diagnostics of this decease and immediately applied treatment entails better life prognosis for the patient. The goal of this work is to initialize the development of an automated tumour recognition method based on computed tomography images processing. The resulting method is aimed at early glioma diagnostics support by distinguishing between the healthy tissue and the tumour tissue. The proposed technique involves, subsequently, image preprocessing, feature extraction, and classification of the extracted features using an artificial neural network. To obtain features, we compute the skewness of the discrete wavelet transform coefficients from selected rectangular image regions using three neighboring image slices to increase the number of samples while preserving good segmentation resolution within the image. The segmentation results are evaluated in cooperation with the neurologist.

Název v anglickém jazyce

Brain Tumour Diagnostics Support Based on Medical Image Segmentation

Popis výsledku anglicky

High-grade gliomas represent rapidly growing malignant brain tumours. Early diagnostics of this decease and immediately applied treatment entails better life prognosis for the patient. The goal of this work is to initialize the development of an automated tumour recognition method based on computed tomography images processing. The resulting method is aimed at early glioma diagnostics support by distinguishing between the healthy tissue and the tumour tissue. The proposed technique involves, subsequently, image preprocessing, feature extraction, and classification of the extracted features using an artificial neural network. To obtain features, we compute the skewness of the discrete wavelet transform coefficients from selected rectangular image regions using three neighboring image slices to increase the number of samples while preserving good segmentation resolution within the image. The segmentation results are evaluated in cooperation with the neurologist.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2009

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings 17th Annual Conference Technical Computing Prague 2009

ISBN

978-80-7080-733-0

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

—

Název nakladatele

Humusoft

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

19. 11. 2009

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—