prikaz prve stranice dokumenta Segmentacija tumora mozga 3D U-Net Arhitekturom
Access restricted to authenticated users
master's thesis
Segmentacija tumora mozga 3D U-Net Arhitekturom
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:708706
Ivić, Filip
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Ivić, F. (2022). Segmentacija tumora mozga 3D U-Net Arhitekturom (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:708706

Ivić, Filip. "Segmentacija tumora mozga 3D U-Net Arhitekturom." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:708706

Ivić, Filip. "Segmentacija tumora mozga 3D U-Net Arhitekturom." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:708706

Ivić, F. (2022). 'Segmentacija tumora mozga 3D U-Net Arhitekturom', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 11 July 2024, https://urn.nsk.hr/urn:nbn:hr:179:708706

Ivić F. Segmentacija tumora mozga 3D U-Net Arhitekturom [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 July 11] Available at: https://urn.nsk.hr/urn:nbn:hr:179:708706

F. Ivić, "Segmentacija tumora mozga 3D U-Net Arhitekturom", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:708706

Metadata
TitleSegmentacija tumora mozga 3D U-Net Arhitekturom
Title (english)Brain tumor segmentation using 3D U-Net architecture
AuthorFilip Ivić
MentorMaja Štula https://orcid.org/0000-0003-3954-7049 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Zadatak ovoga diplomskog rada bilo je proučiti 3D U-Net okruženje za segmentaciju 3D slika, opisati 3D U-Net segmentacijsku arhitekturu baziranu na konvolucijskoj neuronskoj mreži (CNN) i razviti vlastiti model koji će segmentirati tumore mozga sa ulaznih slika. Za bolje razumijevanje 3D U-Net okruženja i razvijanja modela, kroz jednostavne i intuitivne primjere objašnjeni su osnovni principi rada neuronskih i konvolucijskih mreža, a zatim i programska implementacija modela u Python programskom jeziku i TensorFlow okruženju. Rezultati segmentacije tumora mozga modela veoma su slični rezultatima ručne segmentacije tumora mozga iskusnih radiologa iz čega se da zaključiti da je model dobro napravljen.
Abstract (english)
The task of this work was to study the 3D U-Net environment for segmentation of 3D images, to describe the 3D U-Net segmentation architecture based on a convolutional neural network (CNN) and to develop an own model that will segment brain tumors from input images. For a better understanding of the 3D U-Net environment and model development, the basic principles of neural and convolutional networks are explained through simple and intuitive examples, followed by the programmatic implementation of the model in the Python programming language and TensorFlow environment. The results of brain tumor segmentation of the model are very similar to the results of manual brain tumor segmentation by experienced radiologists, from which we can conclude that the model is well made.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:708706
Study programmeTitle: Computing
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 authenticated users
Terms of useLicence In copyright icon
Created on2023-05-17 12:59:35