Model strojnog učenja za klasifikaciju Alzheimerove bolesti uporabom slika magnetske rezonancije mozga

undergraduate thesis

• Title (english): A machine learning model for the Alzheimer's disease classification using brain magnetic resonance images
• Author: Petra Buršić
• Mentor: Jelena Božek (mentor)
• Committee member: Jelena Božek (predsjednik povjerenstva)
• Committee member: Sonja Grgić (član povjerenstva)
• Committee member: Ivana Žeger (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad istražuje primjenu strojnog učenja za klasifikaciju Alzheimerove bolesti koristeći strukturne MRI slike iz ADNI baze podataka. Implementirani su modeli stabla odluke, nasumične šume i stroja potpornih vektora. Model nasumične šume postiže točnost od 69%, dok stroj potpornih vektora postiže 66%, a stablo odluke 68%. Usporedba s relevantnim radovima iz literature pokazuje da naši modeli ostvaruju konkurentne rezultate, ali postoji prostor za poboljšanje, posebno u klasifikaciji slučajeva s blagim kognitivnim oštećenjem.

Abstract (english)

This paper explores the application of machine learning for the classification of Alzheimer's disease using structural MRI images from the ADNI database. Implemented models include Decision Tree, Random Forest and Support Vector Machine. The Random Forest model achieves an accuracy of 69%, while Support Vector Machine achieves 66% and Decision Tree achieves 68%. The comparison with relevant literature indicates that our models achieve competitive results, though there is room for improvement, particularly in classifying mild cognitive impairment.

• Keywords: Strojno učenje; Alzheimerova bolest; Klasifikacija; Stablo odluke; Slučajna šuma; Stroj potpornih vektora; MRI; strukturni MRI
• Keywords (english): Machine learning; Alzheimer's disease; Classification; Decision Tree; Random Forest; Support Vector Machine; MRI; structural MRI
• Language: croatian
• URN:NBN: urn:nbn:hr:168:798564
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-12 20:15:08