Image of IMPLEMENTASI ALGORITMA YOU ONLY LOOK ONCE (YOLO) PADA CITRA MAGNETIC RESONANCE IMAGING (MRI) UNTUK DETEKSI TUMOR OTAK

Skripsi

IMPLEMENTASI ALGORITMA YOU ONLY LOOK ONCE (YOLO) PADA CITRA MAGNETIC RESONANCE IMAGING (MRI) UNTUK DETEKSI TUMOR OTAK

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Limitations of visual analysis by medical personnel. This study implements the YOLOv8 algorithm, a state-of-the-art deep learning method for object detection, to identify three types of brain tumors, namely glioma, meningioma, and pituitary. The dataset was obtained from Kaggle, then processed through the preprocessing and augmentation stages with Roboflow, and trained using several YOLOv8 variants (n, s, m, l) with hyperparameter tuning. Evaluation using precision, recall, mAP50, and mAP50-95 metrics. The results show that the YOLOv8s-E100-B64 model produces the best performance with a precision of 0.943, recall of 0.876, mAP50 of 0.94, and mAP50-95 of 0.744. This model is proven to be fast, accurate, and stable in all stages of testing, making it potential as a diagnostic tool based on MRI images. Keywords: Brain Tumor, YOLOv8, MRI Image, Deep Learning, Roboflow

Availability
Inventory Code Barcode Call Number Location Status
2507005555T183564T1835642025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1835642025
Publisher
Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xvi, 82 hlm.; ilus,; tab, 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
004.920 7
Content Type
Text
Media Type
unmediated
Carrier Type
other (computer)
Edition
-
Subject(s)
Prodi Sistem Komputer
Aplikasi komputer dalam pengolahan citra dan medis
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment