Brain tumor detection using combined deep learning models

dc.contributor.authorBARKAT AYA
dc.contributor.authorENC/ Brik Youcef
dc.date.accessioned2024-07-15T10:07:54Z
dc.date.available2024-07-15T10:07:54Z
dc.date.issued2024-07-15
dc.description.abstractEN Deep learning greatly enhances our daily lives and health. Recently, medical professionals have used these techniques to treat brain tumors due to their strong data analysis capabilities. This research proposes a system for detecting and classifying brain tumors using advanced deep learning models. Using the Br35H dataset with MRI images classified into glioma, meningioma, pituitary tumor, and no tumor, we tested ResNet50V2, MobileNetV2, DenseNet169, and two composite models. The results showed high accuracy and efficiency in classifying brain tumors FR Le deep learning am´eliore notre vie et notre sant´e. R´ecemment, des professionnels de la sant´e ont utilis´e ces techniques pour traiter les tumeurs c´er´ebrales grˆace `a leurs capacit´es d’analyse de donn´ees. Cette recherche propose un syst`eme de d´etection et de classification des tumeurs c´er´ebrales avec des mod`eles de deep learning avanc´es. En utilisant le jeu de donn´ees Br35H et les mod`eles ResNet50V2, MobileNetV2, DenseNet169 et deux mod`eles composites, les r´esultats ont montr´e une grande pr´ecision et efficacit´e dans la classification des tumeurs c´er´ebrales.
dc.identifier.urihttps://depot.univ-msila.dz/handle/123456789/43775
dc.language.isoen
dc.publisherUniversity of M'sila
dc.relation.ispartofseries2024
dc.subjectBrain tumor
dc.subjectimage classification
dc.subjectdeep learning
dc.subjectartificial intelligence
dc.subjectmedical imaging
dc.titleBrain tumor detection using combined deep learning models
dc.typeThesis

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Mémoire BARKAT AYA Electronique Master 2024.pdf
Size:
5.08 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections