Publication detail

A Tool for Automatic Estimation of Patient Position in Spinal CT Data

JAKUBÍČEK, R. VIČAR, T. CHMELÍK, J.

Original Title

A Tool for Automatic Estimation of Patient Position in Spinal CT Data

Type

conference paper

Language

English

Original Abstract

Most of the recently available research and challenge data lack the meta-data containing any information about the patient position. This paper presents a tool for automatic rotation of CT data into a standardized (Head First Supine) patient position. The proposed method is based on the prediction of rotation angle with convolutional neural network, and it achieved nearly perfect results with an accuracy of 99.55 %. We provide implementations with easy to use example for both, Matlab and Python (PyTorch), which can be used, for example, for automatic rotation correction of VerSe2020 challenge data.

Keywords

Patient position estimation; Convolutional neural network; Computed tomography

Authors

JAKUBÍČEK, R.; VIČAR, T.; CHMELÍK, J.

Released

30. 11. 2020

Publisher

Springer Nature Switzerland AG 2021

Location

Switzerland

ISBN

978-3-030-64610-3

Book

EMBEC 2020, IFMBE Proceedings 80

ISBN

1680-0737

Periodical

IFMBE PROCEEDINGS

Year of study

80

State

Kingdom of Sweden

Pages from

51

Pages to

56

Pages count

6

URL

https://link.springer.com/chapter/10.1007/978-3-030-64610-3_7

BibTex

@inproceedings{BUT166032,
  author="Roman {Jakubíček} and Tomáš {Vičar} and Jiří {Chmelík}",
  title="A Tool for Automatic Estimation of Patient Position in Spinal CT Data",
  booktitle="EMBEC 2020, IFMBE Proceedings 80",
  year="2020",
  journal="IFMBE PROCEEDINGS",
  volume="80",
  pages="51--56",
  publisher="Springer Nature Switzerland AG 2021",
  address="Switzerland",
  doi="10.1007/978-3-030-64610-3\{_}7",
  isbn="978-3-030-64610-3",
  issn="1680-0737",
  url="https://link.springer.com/chapter/10.1007/978-3-030-64610-3_7"
}