Enhancing CT 3D Images by Independent Component Analysis of Projection Images

Markus Hannula; Jari A.K. Hyttinen; Jarno M.A. Tanskanen

doi:10.1007/978-3-030-31635-8_46

Enhancing CT 3D Images by Independent Component Analysis of Projection Images

Markus Hannula, Jari A.K. Hyttinen, Jarno M.A. Tanskanen

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

8 Lataukset (Pure)

Abstrakti

Computed tomography (CT) is an imaging modality producing 3D images from sets of 2D X-ray images taken around the object. The images are noisy by nature, and segmentation of the 3D images is tedious. Also, detection of low contrast objects may be difficult, if not impossible. Here, we propose an independent component analysis (ICA) based method to process sets of 2D projection images prior to 3D reconstruction to remove noise, and to enhance objects for detection and segmentation. In this paper, a proof-of-concept is provided: the proposed method was able to separate noise and image components, as well as to make visible objects that were not observable in 3D images without processing. We demonstrate our method in object separation with 2D slice image processing simulations, and by enhancing a 3D image of a polymer sample taken with Xradia MicroXCT-400. The method is applicable in any CT tomography for which a number of project image sets with different contrasts can be taken, e.g., in multispectral fashion.

Alkuperäiskieli	Englanti
Otsikko	15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019
Toimittajat	Jorge Henriques, Paulo de Carvalho, Nuno Neves
Kustantaja	Springer
Sivut	381-389
Sivumäärä	9
ISBN (painettu)	978-3-030-31634-1
DOI - pysyväislinkit	https://doi.org/10.1007/978-3-030-31635-8_46
Tila	Julkaistu - 2020
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	Mediterranean Conference on Medical and Biological Engineering and Computing - Kesto: 1 tammik. 2020 → …

Julkaisusarja

Nimi	IFMBE Proceedings
Vuosikerta	76
ISSN (painettu)	1680-0737

Conference

Conference	Mediterranean Conference on Medical and Biological Engineering and Computing
Ajanjakso	1/01/20 → …

Rahoitus

The work of J. M. A. Tanskanen has been supported by Jane and Aatos Erkko Foundation, Finland, under the project Biological Neuronal Communications and Computing with ICT. The work of M. Hannula has been supported by the Human Spare Parts Project funded by Finnish Funding Agency for Technology and Innovation (TEKES).

Tutkimusalat

3D imaging
CT
Computed tomography
Image processing
Independent component analysis
Micro-CT
µCT

Julkaisufoorumi-taso

Jufo-taso 1

Pääsy asiakirjaan

10.1007/978-3-030-31635-8_46

133_MEDICON_Tanskanen_selfarchiveAccepted author manuscript, 4,42 MB

http://urn.fi/URN:NBN:fi:tuni-202103052388

Siteeraa tätä

Hannula, M., Hyttinen, J. A. K., & Tanskanen, J. M. A. (2020). Enhancing CT 3D Images by Independent Component Analysis of Projection Images. teoksessa J. Henriques, P. de Carvalho, & N. Neves (Toimittajat), 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019 (Sivut 381-389). (IFMBE Proceedings; Vuosikerta 76). Springer. https://doi.org/10.1007/978-3-030-31635-8_46

Hannula, Markus ; Hyttinen, Jari A.K. ; Tanskanen, Jarno M.A. / Enhancing CT 3D Images by Independent Component Analysis of Projection Images. 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019. Toimittaja / Jorge Henriques ; Paulo de Carvalho ; Nuno Neves. Springer, 2020. Sivut 381-389 (IFMBE Proceedings).

@inproceedings{ba2e031f6e4c4ed891d321452c45188b,

title = "Enhancing CT 3D Images by Independent Component Analysis of Projection Images",

abstract = "Computed tomography (CT) is an imaging modality producing 3D images from sets of 2D X-ray images taken around the object. The images are noisy by nature, and segmentation of the 3D images is tedious. Also, detection of low contrast objects may be difficult, if not impossible. Here, we propose an independent component analysis (ICA) based method to process sets of 2D projection images prior to 3D reconstruction to remove noise, and to enhance objects for detection and segmentation. In this paper, a proof-of-concept is provided: the proposed method was able to separate noise and image components, as well as to make visible objects that were not observable in 3D images without processing. We demonstrate our method in object separation with 2D slice image processing simulations, and by enhancing a 3D image of a polymer sample taken with Xradia MicroXCT-400. The method is applicable in any CT tomography for which a number of project image sets with different contrasts can be taken, e.g., in multispectral fashion.",

keywords = "3D imaging, CT, Computed tomography, Image processing, Independent component analysis, Micro-CT, µCT, 3D imaging, CT, Computed tomography, Image processing, Independent component analysis, Micro-CT, µCT",

author = "Markus Hannula and Hyttinen, {Jari A.K.} and Tanskanen, {Jarno M.A.}",

note = "dupl=51710539; Mediterranean Conference on Medical and Biological Engineering and Computing ; Conference date: 01-01-2020",

year = "2020",

doi = "10.1007/978-3-030-31635-8_46",

language = "English",

isbn = "978-3-030-31634-1",

series = "IFMBE Proceedings",

publisher = "Springer",

pages = "381--389",

editor = "Jorge Henriques and {de Carvalho}, Paulo and Nuno Neves",

booktitle = "15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019",

}

Hannula, M , Hyttinen, JAK & Tanskanen, JMA 2020, Enhancing CT 3D Images by Independent Component Analysis of Projection Images. julkaisussa J Henriques, P de Carvalho & N Neves (toim), 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019. IFMBE Proceedings, Vuosikerta 76, Springer, Sivut 381-389, Mediterranean Conference on Medical and Biological Engineering and Computing, 1/01/20. https://doi.org/10.1007/978-3-030-31635-8_46

Enhancing CT 3D Images by Independent Component Analysis of Projection Images. / Hannula, Markus ; Hyttinen, Jari A.K.; Tanskanen, Jarno M.A.
15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019. toim. / Jorge Henriques; Paulo de Carvalho; Nuno Neves. Springer, 2020. s. 381-389 (IFMBE Proceedings; Vuosikerta 76).

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - Enhancing CT 3D Images by Independent Component Analysis of Projection Images

AU - Hannula, Markus

AU - Hyttinen, Jari A.K.

AU - Tanskanen, Jarno M.A.

N1 - dupl=51710539

PY - 2020

Y1 - 2020

N2 - Computed tomography (CT) is an imaging modality producing 3D images from sets of 2D X-ray images taken around the object. The images are noisy by nature, and segmentation of the 3D images is tedious. Also, detection of low contrast objects may be difficult, if not impossible. Here, we propose an independent component analysis (ICA) based method to process sets of 2D projection images prior to 3D reconstruction to remove noise, and to enhance objects for detection and segmentation. In this paper, a proof-of-concept is provided: the proposed method was able to separate noise and image components, as well as to make visible objects that were not observable in 3D images without processing. We demonstrate our method in object separation with 2D slice image processing simulations, and by enhancing a 3D image of a polymer sample taken with Xradia MicroXCT-400. The method is applicable in any CT tomography for which a number of project image sets with different contrasts can be taken, e.g., in multispectral fashion.

AB - Computed tomography (CT) is an imaging modality producing 3D images from sets of 2D X-ray images taken around the object. The images are noisy by nature, and segmentation of the 3D images is tedious. Also, detection of low contrast objects may be difficult, if not impossible. Here, we propose an independent component analysis (ICA) based method to process sets of 2D projection images prior to 3D reconstruction to remove noise, and to enhance objects for detection and segmentation. In this paper, a proof-of-concept is provided: the proposed method was able to separate noise and image components, as well as to make visible objects that were not observable in 3D images without processing. We demonstrate our method in object separation with 2D slice image processing simulations, and by enhancing a 3D image of a polymer sample taken with Xradia MicroXCT-400. The method is applicable in any CT tomography for which a number of project image sets with different contrasts can be taken, e.g., in multispectral fashion.

KW - 3D imaging

KW - CT

KW - Computed tomography

KW - Image processing

KW - Independent component analysis

KW - Micro-CT

KW - µCT

KW - 3D imaging

KW - CT

KW - Computed tomography

KW - Image processing

KW - Independent component analysis

KW - Micro-CT

KW - µCT

U2 - 10.1007/978-3-030-31635-8_46

DO - 10.1007/978-3-030-31635-8_46

M3 - Conference contribution

AN - SCOPUS:85075871982

SN - 978-3-030-31634-1

T3 - IFMBE Proceedings

SP - 381

EP - 389

BT - 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019

A2 - Henriques, Jorge

A2 - de Carvalho, Paulo

A2 - Neves, Nuno

PB - Springer

T2 - Mediterranean Conference on Medical and Biological Engineering and Computing

Y2 - 1 January 2020

ER -

Hannula M , Hyttinen JAK , Tanskanen JMA. Enhancing CT 3D Images by Independent Component Analysis of Projection Images. julkaisussa Henriques J, de Carvalho P, Neves N, toimittajat, 15th Mediterranean Conference on Medical and Biological Engineering and Computing – MEDICON 2019 - Proceedings of MEDICON 2019. Springer. 2020. s. 381-389. (IFMBE Proceedings). doi: 10.1007/978-3-030-31635-8_46

Enhancing CT 3D Images by Independent Component Analysis of Projection Images

Abstrakti

Julkaisusarja

Conference

Rahoitus

Tutkimusalat

Julkaisufoorumi-taso

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä