prikaz prve stranice dokumenta Segmentacija jezgara stanica primjenom U-net arhitekture
Access restricted to authenticated users
undergraduate thesis
Segmentacija jezgara stanica primjenom U-net arhitekture
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:703569
Baljak, Matej
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

Baljak, M. (2022). Segmentacija jezgara stanica primjenom U-net arhitekture (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:703569

Baljak, Matej. "Segmentacija jezgara stanica primjenom U-net arhitekture." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:703569

Baljak, Matej. "Segmentacija jezgara stanica primjenom U-net arhitekture." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:703569

Baljak, M. (2022). 'Segmentacija jezgara stanica primjenom U-net arhitekture', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 02 December 2024, https://urn.nsk.hr/urn:nbn:hr:179:703569

Baljak M. Segmentacija jezgara stanica primjenom U-net arhitekture [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 December 02] Available at: https://urn.nsk.hr/urn:nbn:hr:179:703569

M. Baljak, "Segmentacija jezgara stanica primjenom U-net arhitekture", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:703569

Metadata
TitleSegmentacija jezgara stanica primjenom U-net arhitekture
Title (english)Cell nuclei segmenation using U-net architecture
AuthorMatej Baljak
MentorMatko Šarić https://orcid.org/0000-0001-9752-9653 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Electronics
Abstract
U ovome radu je obrađena segmentacija jezgra stanica u primjenom U-net arhitekture. Prvo je definirana primjena i važnost segmentacije medicinskih slika. Segmentacija medicinskih slika je važna jer omogućuje liječnicima analizu medicinskih slika na način koji nikada ne bi mogli golim okom. U teorijskom dijelu rada definirane su konvolucijske neuronske mreže te njihove vrste i primjena. Konvolucijske neuronske mreže su postale standardne mreže za segmentaciju i svakodnevno se unaprjeđuju. Nakon toga je posebno obrađena U-net arhitektura koja se pokazala najboljom u području medicinske segmentacije. Također je posebno predstavljen unaprijeđeni model U-net arhitekturu koji posjeduje veću učinkovitost i preciznost Na kraju je primjenom programskog jezika Python i biblioteke Keras napravljen proces treniranja kako bi se mogla provesti segmentacija slika jezgara stanica.
Abstract (english)
In this paper, the segmentation of nuclei cells in the application of the U-net architecture is discussed. First, the application and importance of medical image segmentation is defined. Medical image segmentation is important because it allows doctors to analyze medical images in a way that they could never do with the naked eye. Convolutional neural networks and their types and applications are defined in the theoretical part of the paper. Convolutional neural networks have become the standard segmentation networks and are being improved every day. After that, the U-net architecture, which proved to be the best in the field of medical segmentation, was specially analyzed. An improved model of the U-net architecture, which has greater efficiency and precision, was also specially presented. Finally, using the Python programming language and the Keras library, a training process was made in order to be able to perform the segmentation of images of cell nuclei.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:703569
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-02-20 12:46:23