Publication detail

OBJECT DETECTION NETWORKS FOR LOCALIZATION AND CLASSIFICATION OF INTRACRANIAL HEMORRHAGES

NEMČEK, J.

Original Title

OBJECT DETECTION NETWORKS FOR LOCALIZATION AND CLASSIFICATION OF INTRACRANIAL HEMORRHAGES

Type

conference paper

Language

English

Original Abstract

Intracranialhemorrhagesrepresentlife-threateningbraininjuries.Thispaperpresentstwo state-of-the-artobjectdetectionsystems(FasterR-CNNandYOLOv2)whicharetrainedtolocalize andclassifyhemorrhagesinaxialheadCTslicesbyprovidinglabelledrectangularboundingboxes. PubliclyavailabledatasetsofheadCTdataandgroundtruthboundingboxesareusedtoevaluateand comparetheperformanceofbothdetectors.TheFasterR-CNNshowsbetterresultsbyachievingan averageJaccardcoefficientof58.7%.

Keywords

intracranialhemorrhage,convolutionalneuralnetwork,localization,classification,computedtomography,FasterR-CNN,YOLOv2

Authors

NEMČEK, J.

Released

27. 4. 2021

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-5943-4

Book

PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers

Edition

1

Pages from

116

Pages to

120

Pages count

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf

BibTex

@inproceedings{BUT183915,
  author="Jakub {Nemček}",
  title="OBJECT DETECTION NETWORKS FOR LOCALIZATION AND CLASSIFICATION OF INTRACRANIAL HEMORRHAGES",
  booktitle="PROCEEDINGS II OF THE 27TH STUDENT EEICT 2021 selected papers",
  year="2021",
  series="1",
  pages="116--120",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  doi="10.13164/eeict.2021.116",
  isbn="978-80-214-5943-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf"
}