Publication detail

Comparison of full-size and patches-based learning approaches for aneurysm segmentation in TOF-MRI data

VÝVODA, J. JAKUBÍČEK, R.

Original Title

Comparison of full-size and patches-based learning approaches for aneurysm segmentation in TOF-MRI data

Type

conference paper

Language

English

Original Abstract

The paper is interested in segmentation of intracranial aneurysms. Intracranial aneurysms are life-threatening issue. In this paper there are proposed two methods for this segmentation problem. First one is segmentation with use of full size images, the other one uses patches of the image, which could help decrease the ration between pixels representing background and pixels representing aneurysms. Data from ADAM challenge 2020 are used to train and evaluate these approaches. Using full images show better results in dice coefficient, which is 0.16 greater, then patched image approach.

Keywords

Intracranial aneurysm, aneurysm, machine learning, detection, magnetic resonance, U-net, segmentation

Authors

VÝVODA, J.; JAKUBÍČEK, R.

Released

26. 4. 2022

Publisher

Brno University of Technology, Faculty of Electronic Engineering and Communication

Location

Brno

ISBN

978-80-214-6029-4

Book

Proceedings I of the 28th Conference STUDENT EEICT 2022 General papers

Edition

1

Pages from

247

Pages to

250

Pages count

4

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1_v2.pdf

BibTex

@inproceedings{BUT188038,
  author="Jan {Vývoda} and Roman {Jakubíček}",
  title="Comparison of full-size and patches-based learning approaches for aneurysm segmentation in TOF-MRI data",
  booktitle="Proceedings I of the 28th Conference STUDENT EEICT 2022 General papers",
  year="2022",
  series="1",
  pages="247--250",
  publisher="Brno University of Technology, Faculty of Electronic Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6029-4",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_1_v2.pdf"
}