prikaz prve stranice dokumenta Prijenos znanja u analizi medicinskih slika
Access restricted to students and staff of home institution
master's thesis
Prijenos znanja u analizi medicinskih slika
2017. urn:nbn:hr:190:594917
Burul, Matko
University of Rijeka
Faculty of Engineering

Cite this document

Burul, M. (2017). Prijenos znanja u analizi medicinskih slika (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:594917

Burul, Matko. "Prijenos znanja u analizi medicinskih slika." Master's thesis, University of Rijeka, Faculty of Engineering, 2017. https://urn.nsk.hr/urn:nbn:hr:190:594917

Burul, Matko. "Prijenos znanja u analizi medicinskih slika." Master's thesis, University of Rijeka, Faculty of Engineering, 2017. https://urn.nsk.hr/urn:nbn:hr:190:594917

Burul, M. (2017). 'Prijenos znanja u analizi medicinskih slika', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 12 July 2024, https://urn.nsk.hr/urn:nbn:hr:190:594917

Burul M. Prijenos znanja u analizi medicinskih slika [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2017 [cited 2024 July 12] Available at: https://urn.nsk.hr/urn:nbn:hr:190:594917

M. Burul, "Prijenos znanja u analizi medicinskih slika", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:190:594917

Please login to the repository to save this object to your list.
Metadata
TitlePrijenos znanja u analizi medicinskih slika
AuthorMatko Burul
MentorIvan Štajduhar (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2017-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu obrađeno je stvaranje skupa podataka medicinskih slika u svrhu njihova korištenja za treniranje i evaluaciju klasifikacijskih modela. Trenirani modeli uključuju konvolucijske neuronske mreže inicijalizirane pomoću tehnike prijenosa znanja i mreže inicijalizirane nasumičnim vrijednostima. Prikazani su i analizirani rezultati dobivenih modela, te su, pomoću tehnike prijenosa znanja iz tih modela, istrenirani i modeli za klasifikaciju ozljede koljena iz volumetrijskih podataka čiji su rezultati također obrađeni.
Abstract (english)
In this work, the creation of a medical images dataset was explained. The dataset was used to train and evaluate several classification modela based on convolutional neural networks initialized with random values or through transfer learning. The results are shown and analysed. A second set of models, used to classify knee injury from volumetric data, was trained using transfer learning from the previous models. The results of these models are shown and analysed as well.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:594917
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 on2017-07-19 12:39:52