| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Segmentacija slik celic z algoritmi globokega učenja : magistrsko delo
Authors:ID Gorjanc, Gregor (Author)
ID Karakatič, Sašo (Mentor) More about this mentor... New window
ID Pohorec, Viljem (Comentor)
Files:.pdf MAG_Gorjanc_Gregor_2023.pdf (10,66 MB)
MD5: A9B32D39F78502BF6A5A0CEE65CDFC10
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu smo se spoznali s problematiko sladkorne bolezni, ki se odraža z nepravilnim obnašanjem celic beta v trebušni slinavki. Seznanili smo se s postopkom označevanja slik Langerhansovih otočkov, ki vsebujejo celice beta. S ciljem avtomatizacije procesa ročnega označevanja slik smo se odločili za uporabo globoke nevronske mreže za segmentacijo slik. Po analizi podatkovnih množic in preobrazbi slikovnih vrst s postopki agregacije v obliko, primerno za strojno učenje slik, smo s pomočjo nenadzorovanega učenja naučili nevronsko mrežo W-Net in ovrednotili rezultate. Mreža je uspešno identificirala zanimiva območja na slikah, vendar s premalo natančnostjo in prevelikimi območji lažno pozitivnih slikovnih točk.
Keywords:segmentacija slik, nenadzorovano učenje, W-Net, nevronska mreža, celice beta
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[G. Gorjanc]
Year of publishing:2022
Number of pages:1 spletni vir (1 datoteka PDF (XIV, 123 f.))
PID:20.500.12556/DKUM-83576 New window
UDC:004.85.021:004.92(043.2)
COBISS.SI-ID:148612867 New window
Publication date in DKUM:23.01.2023
Views:1023
Downloads:146
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:30.12.2022

Secondary language

Language:English
Title:Cell image segmentation with deep learning algorithms
Abstract:In this master’s thesis, we acquaint ourselves with the challenges of diabetes mellitus, which is expressed by abnormal behaviour of beta cells in the pancreas. We familiarised ourselves with the process of labelling images of islets of Langerhans, which contain beta cells. With the aim of automating manual labelling process, we decided to use a deep neural network for image segmentation. After analysing the datasets and transforming the image series with aggregation techniques into appropriate format, we used unsupervised learning to train W-Net neural network and evaluate results. Neural network was successful in identifying areas of interests in images, but with insufficient precision and large areas of false positive pixels.
Keywords:image segmentation, unsupervised learning, W-Net, neural net, beta cells


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica