prikaz prve stranice dokumenta Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke
Access restricted to students and staff of home institution
master's thesis
Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke
2020. urn:nbn:hr:190:882406
Žužić, Ivana
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Intelligent Computing Systems

Cite this document

Žužić, I. (2020). Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:882406

Žužić, Ivana. "Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:882406

Žužić, Ivana. "Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:882406

Žužić, I. (2020). 'Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 27 April 2024, https://urn.nsk.hr/urn:nbn:hr:190:882406

Žužić I. Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2020 [cited 2024 April 27] Available at: https://urn.nsk.hr/urn:nbn:hr:190:882406

I. Žužić, "Generativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:190:882406

Please login to the repository to save this object to your list.
Metadata
TitleGenerativne suparničke mreže za dodavanje i uklanjanje gipsa s RTG slika ruke
Title (english)Generative adversarial networks for adding and removing casts from hand X-ray images
AuthorIvana Žužić
MentorIvan Štajduhar (mentor)
Committee memberGoran Mauša (predsjednik povjerenstva)
Committee memberSandi Ljubić (član povjerenstva)
Committee memberIvan Štajduhar (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Intelligent Computing Systems)
Rijeka
Defense date and country2020-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj diplomski rad daje pregled korištenja generativnih suparničkih mreža u području slika za medicinsku dijagnostiku i nudi metodu dodavanja i micanja gipsa s RTG-slika ruku pomoću CycleGAN-a. Nekoliko CycleGAN modela s razlikama u arhitekturi isprobana su i uspoređena prema postignutoj distribuciji boja i procijenjeni od strane iskusnog radiologa. Rezultati su pokazali da je CycleGAN koji koristi U-Net za stvaranje slika veličine 512x512 najkorisniji za radiologa i ima najbližu distribuciju boja originalnoj distribuciji.
Abstract (english)
This thesis gives an overview of generative adversarial networks usage in the field of medical diagnostic imaging and offers a method of adding and removing cast from Xray images of hands using CycleGAN. Multiple CycleGAN models with architectural differences have been tried out and their performance has been compared in terms of achieved colour distribution and evaluated by an experienced radiologist. The results showed that the CycleGAN using U-Net for 512x512 images generation was the most useful for the radiologist and had the closest colour distribution to the original one.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:882406
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-12-16 11:59:27