Titre :	Deep Learning Model for Brain Tumor Radiogenomic Classification
Type de document :	texte imprimé
Auteurs :	hadjer Ouarem, Auteur ; aymen mohamed Sraouia, Auteur ; khaled Nasri, Directeur de thèse
Année de publication :	2022
Importance :	1 vol (67 f .)
Format :	29cm
Langues :	Français (fre)
Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Informatique
Index. décimale :	004 Informatique
Résumé :	For malignant brain tumor (Glioblastoma), known as the worst prognosis, with median survival being less than a year, recent medical research demonstrates that the presence of a specific genetic sequence in the tumor known as MGMT promoter methylation has been shown to be a favorable prognostic factor and a strong predictor of responsiveness to chemotherapy. The problem is that traditional methodology of surgery to extract a sample to be analyzed is very complicated for brain tumors cases, and takes long time. In this work we will explore the efficiency of Deep Learning based methodology to detect the existence of specific genomic sequences from MRI images. This alternative can be very useful and can help many cases to be treated. We have used many pretrained models and many images sequences to realize our experiences, to improve our models and determine which image sequence is the best to detect MGMT genome from MRI data.
Côte titre :	MAI/0584
En ligne :	https://drive.google.com/file/d/1vIJffysvjMQk-H2jqZA5t7HgVVIUBnUb/view?usp=share [...]
Format de la ressource électronique :	pdf

Deep Learning Model for Brain Tumor Radiogenomic Classification [texte imprimé] / hadjer Ouarem, Auteur ; aymen mohamed Sraouia, Auteur ; khaled Nasri, Directeur de thèse . - 2022 . - 1 vol (67 f .) ; 29cm.
Langues : Français (fre)

Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Informatique
Index. décimale :	004 Informatique
Résumé :	For malignant brain tumor (Glioblastoma), known as the worst prognosis, with median survival being less than a year, recent medical research demonstrates that the presence of a specific genetic sequence in the tumor known as MGMT promoter methylation has been shown to be a favorable prognostic factor and a strong predictor of responsiveness to chemotherapy. The problem is that traditional methodology of surgery to extract a sample to be analyzed is very complicated for brain tumors cases, and takes long time. In this work we will explore the efficiency of Deep Learning based methodology to detect the existence of specific genomic sequences from MRI images. This alternative can be very useful and can help many cases to be treated. We have used many pretrained models and many images sequences to realize our experiences, to improve our models and determine which image sequence is the best to detect MGMT genome from MRI data.
Côte titre :	MAI/0584
En ligne :	https://drive.google.com/file/d/1vIJffysvjMQk-H2jqZA5t7HgVVIUBnUb/view?usp=share [...]
Format de la ressource électronique :	pdf