Publication result detail

Iterative machine learning based rotational alignment of brain 3D CT data

CHMELÍK, J.; JAKUBÍČEK, R.; VIČAR, T.; WALEK, P.; OUŘEDNÍČEK, P.; JAN, J.

Original Title

Iterative machine learning based rotational alignment of brain 3D CT data

English Title

Iterative machine learning based rotational alignment of brain 3D CT data

Type

Paper in proceedings (conference paper)

Original Abstract

The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (1 degree) and in a significantly shorter time than the experts (2 minutes per case).

English abstract

The optimal rotational alignment of brain Computed Tomography (CT) images to a required standard position has a crucial importance for both automatic and manual diagnostic analysis. In this contribution, we present a novel two-step iterative approach for the automatic 3D rotational alignment of brain CT data. The angles of axial and coronal rotations are determined by an unsupervised by localisation of the Midsagittal Plane (MSP) method. This includes detection and pairing of medially symmetrical feature points. The sagittal rotation angle is subsequently estimated by regression convolutional neural network (CNN). The proposed methodology has been evaluated on a dataset of CT data manually aligned by radiologists. It has been shown that the algorithm achieved the low error of estimated rotations (1 degree) and in a significantly shorter time than the experts (2 minutes per case).

Keywords

CT; brain; alignement; machine learning

Key words in English

CT; brain; alignement; machine learning

Authors

CHMELÍK, J.; JAKUBÍČEK, R.; VIČAR, T.; WALEK, P.; OUŘEDNÍČEK, P.; JAN, J.

RIV year

2020

Released

07.10.2019

Publisher

IEEE

Location

Berlin, Germany

ISBN

978-1-5386-1312-2

Book

2019 41th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

ISBN

1557-170X

Periodical

Proceedings IEEE EMBC

Volume

19

State

United States of America

Pages from

4404

Pages to

4408

Pages count

5

URL

https://ieeexplore.ieee.org/document/8857858

BibTex

@inproceedings{BUT157792,
  author="Jiří {Chmelík} and Roman {Jakubíček} and Tomáš {Vičar} and Petr {Walek} and Petr {Ouředníček} and Jiří {Jan}",
  title="Iterative machine learning based rotational alignment of brain 3D CT data",
  booktitle="2019 41th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",
  year="2019",
  journal="Proceedings IEEE EMBC",
  volume="19",
  number="19",
  pages="4404--4408",
  publisher="IEEE",
  address="Berlin, Germany",
  doi="10.1109/EMBC.2019.8857858",
  isbn="978-1-5386-1312-2",
  issn="1557-170X",
  url="https://ieeexplore.ieee.org/document/8857858"
}

Documents

EMBC19_1775_MS