
Veuillez utiliser cette adresse pour citer ce document :
http://dspace.univ-tiaret.dz:80/handle/123456789/16905Affichage complet
| Élément Dublin Core | Valeur | Langue |
|---|---|---|
| dc.contributor.author | Larbi, ilyes | - |
| dc.date.accessioned | 2025-11-23T13:52:28Z | - |
| dc.date.available | 2025-11-23T13:52:28Z | - |
| dc.date.issued | 2025-05-27 | - |
| dc.identifier.uri | http://dspace.univ-tiaret.dz:80/handle/123456789/16905 | - |
| dc.description.abstract | Brain tumors are a serious health issue, especially when they're not detected early. Quick diagnosis is really important to improve the chances of survival. MRI scans are very useful for spotting and tracking these tumors, but analyzing the images manually takes a lot of time and can lead to mistakes, especially when the tumors are small or hard to tell apart. That's where deep learning comes in. It can analyze big amounts of data and find patterns that help with tasks like identifying the type of tumor and showing exactly where it is in the brain. This doesn't just make diagnosis faster and more reliable, it also helps doctors create better treatment plans for each patient. In this project, our goal is to build a deep learning system that can do two main things: classify brain MRIs into tumor types like (glioma, meningioma, pituitary tumor, or no tumor), and accurately segment the tumor area. By combining both steps in one smart tool, we hope to make the diagnosis process more efficient and support the use of AI in medical care. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | University of Ibn Khaldoun Tiaret | en_US |
| dc.subject | Brain Tumor | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Transfer Learning | en_US |
| dc.subject | CNN | en_US |
| dc.title | Artificial Intelligence in Malignant Brain Tumor D e tection | en_US |
| dc.type | Thesis | en_US |
| Collection(s) : | Master | |
Fichier(s) constituant ce document :
| Fichier | Description | Taille | Format | |
|---|---|---|---|---|
| TH.M.INF.2025.37.pdf | 7,58 MB | Adobe PDF | Voir/Ouvrir |
Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.