Detail publikace

CELL AND SUB-CELLULAR SEGMENTATION IN QUANTITATIVE PHASE IMAGING USING U-NET

MAJERCIK, J. SPACEK, M.

Originální název

CELL AND SUB-CELLULAR SEGMENTATION IN QUANTITATIVE PHASE IMAGING USING U-NET

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Theabilitytoautomaticallysegmentimages,especiallymicroscopyimagesofcells,opens newopportunitiesincancerresearchorotherpracticalapplications.Recentadvancementsindeep learningenabledforeffectivesingle-cellsegmentation,however,automaticsegmentationofsubcellularregionsisstillchallenging.ThisworkdescribesanimplementationofaU-netneuralnetworkforlabel-freesegmentationofsub-cellularregionsonimagesofadherentprostatecancercells, specificallyPC-3and22Rv1.Usingthebestperformingapproach,outofallthathavebeentested, wehavemanagedtodistinguishbetweenobjectsandbackgroundwithaveragedicecoefficientsof 0.83,0.78and0.63forwholecells,nucleiandnucleolirespectively.

Klíčová slova

cellsegmentation,deeplearning,neuralnetwork,quantitativephaseimaging,nucleus, nucleolus

Autoři

MAJERCIK, J.; SPACEK, M.

Vydáno

27. 4. 2021

Nakladatel

Brno University of Technology, Faculty of Electrical Engineering and Communication

Místo

Brno

ISBN

978-80-214-5943-4

Kniha

PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers

Edice

1

Strany od

9

Strany do

12

Strany počet

4

URL

BibTex

@inproceedings{BUT183885,
  author="Jakub {Majerčík} and Michal {Špaček}",
  title="CELL AND SUB-CELLULAR SEGMENTATION IN QUANTITATIVE PHASE IMAGING USING U-NET",
  booktitle="PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers",
  year="2021",
  series="1",
  pages="9--12",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  doi="10.13164/eeict.2021.9",
  isbn="978-80-214-5943-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf"
}