Otkrivanje tumora na snimkama primjenom dubokih neuronskih mreža

master's thesis

• Title (english): Tumor Detection in Images Using Deep Neural Networks
• Author: Antonio Ilinović
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-04, Croatia

Abstract

U radu su istraženi i opisani modeli neuronskih mreža prikladni za detekciju obje-
kata na slikama, s posebnim naglaskom na model YOLO v8. Preuzet je odgovarajući
skup podataka koji sadržava MRI snimke tumora mozga. Razvijen je sustav za pre-
poznavanje tumora te su opisani korišteni model i postupak učenja. Provedeni su eks-
perimenti za vrednovanje uspješnosti modela na ispitnom skupu, a rezultati su potom
analizirani.

Abstract (english)

The paper investigates and describes neural network models suitable for object de-
tection in images, with a special focus on the YOLO v8 model. An appropriate dataset
containing MRI images of brain tumors was downloaded. A tumor recognition system
was developed, and the used model and learning process were described. Experiments
were conducted to evaluate the model’s performance on the test set, and the results
were then analyzed.

• Keywords: detekcija objekata; MRI; tumor mozga; konvolucijske neuronske mreže; duboko učenje; YOLO v8
• Keywords (english): object detection; MRI; brain tumor; convolutional neural networks; deep learning; YOLO v8
• Language: croatian
• URN:NBN: urn:nbn:hr:168:954551
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-12 20:50:56