Pregled bibliografske jedinice broj: 1131628
Brain tumor detection based on MRI images using multilayer perceptron
Brain tumor detection based on MRI images using multilayer perceptron // Ri-STEM-2021 Proceedings / Lorencin, Ivan ; Baressi Šegota, Sandi ; Car, Zlatan (ur.).
Rijeka, 2021. str. 95-110 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), ostalo)
CROSBI ID: 1131628 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Brain tumor detection based on MRI images using
multilayer perceptron
Autori
Marko Mataija, Dorijan Sablić-Nemec
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), ostalo
Izvornik
Ri-STEM-2021 Proceedings
/ Lorencin, Ivan ; Baressi Šegota, Sandi ; Car, Zlatan - Rijeka, 2021, 95-110
ISBN
978-953-8246-22-7
Skup
International Student Scientific Conference (Ri-STEM 2021)
Mjesto i datum
Rijeka, Hrvatska, 10.06.2021. - 11.06.2021
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Artificial intelligence, Brain tumor, Machine Learning, Multilayer perceptron
Sažetak
The problem of brain tumor detection was approached with the classification of MRI images via the application of a multilayer perceptron, feedforward artificial neural network. Dataset was artificially expanded for training needs and some corrections were done after which images were processed using the Gaussian blur and threshold method. The experiment regarding the fine tuning of the main parameters and neural network architecture was conducted and lead to satisfying results upon application of optimal parameters and architecture.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti, Kliničke medicinske znanosti
POVEZANOST RADA
Ustanove:
Tehnički fakultet, Rijeka
