Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities

Nick Weiss; Johannes Lotz; Jan Modersitzki

doi:10.1007/978-3-662-46224-9_43

Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities

Nick Weiss, Johannes Lotz, Jan Modersitzki

Institute of Mathematics and Image Computing

Abstract

3D reconstruction and digital double staining offer pathologists many new insights into tissue structure and metabolism. Key to these applications is the precise registration of histological slide images, that is challenging in several ways. One major challenge are differently stained slides, that highlight different parts of the tissue. In this paper we introduce a new registration method to face this multimodality. It abstracts the image information to cell nuclei densities. By minimizing the distance of these densities an affine transformation is determined that restores the lost spatial correspondences. The proposed density based registration is evaluated using consecutive histological slides. It is compared to a Mutual Information based registration and shown to be more accurate and robust.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2015
Editors	Heinz Handels, Thomas M. Deserno, Hans-Peter Meinzer, Thomas Tolxdorff
Number of pages	1
Place of Publication	Berlin, Heidelberg
Publisher	Springer Vieweg, Berlin Heidelberg
Publication date	25.02.2015
Pages	245
ISBN (Print)	978-3-662-46223-2
ISBN (Electronic)	978-3-662-46224-9
DOIs	https://doi.org/10.1007/978-3-662-46224-9_43
Publication status	Published - 25.02.2015
Event	Workshop on Bildverarbeitung fur die Medizin 2015 - Universität zu Lübeck, Lübeck, Germany Duration: 15.03.2015 → 17.03.2015

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-662-46224-9_43

Cite this

@inproceedings{3b36dbeb187b4026baa3c3203187ed6d,

title = "Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities",

abstract = "3D reconstruction and digital double staining offer pathologists many new insights into tissue structure and metabolism. Key to these applications is the precise registration of histological slide images, that is challenging in several ways. One major challenge are differently stained slides, that highlight different parts of the tissue. In this paper we introduce a new registration method to face this multimodality. It abstracts the image information to cell nuclei densities. By minimizing the distance of these densities an affine transformation is determined that restores the lost spatial correspondences. The proposed density based registration is evaluated using consecutive histological slides. It is compared to a Mutual Information based registration and shown to be more accurate and robust.",

author = "Nick Weiss and Johannes Lotz and Jan Modersitzki",

year = "2015",

month = feb,

day = "25",

doi = "10.1007/978-3-662-46224-9_43",

language = "English",

isbn = "978-3-662-46223-2",

series = "Informatik aktuell",

publisher = "Springer Vieweg, Berlin Heidelberg",

pages = "245",

editor = "Heinz Handels and Deserno, {Thomas M.} and Hans-Peter Meinzer and Thomas Tolxdorff",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2015",

note = "Workshop on Bildverarbeitung fur die Medizin 2015 ; Conference date: 15-03-2015 Through 17-03-2015",

}

Weiss, N , Lotz, J & Modersitzki, J 2015, Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities. in H Handels, TM Deserno, H-P Meinzer & T Tolxdorff (eds), Bildverarbeitung für die Medizin 2015. Informatik aktuell, Springer Vieweg, Berlin Heidelberg, Berlin, Heidelberg, pp. 245, Workshop on Bildverarbeitung fur die Medizin 2015, Lübeck, Germany, 15.03.15. https://doi.org/10.1007/978-3-662-46224-9_43

Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities. / Weiss, Nick ; Lotz, Johannes ; Modersitzki, Jan.
Bildverarbeitung für die Medizin 2015. ed. / Heinz Handels; Thomas M. Deserno; Hans-Peter Meinzer; Thomas Tolxdorff. Berlin, Heidelberg: Springer Vieweg, Berlin Heidelberg, 2015. p. 245 (Informatik aktuell).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities

AU - Weiss, Nick

AU - Lotz, Johannes

AU - Modersitzki, Jan

PY - 2015/2/25

Y1 - 2015/2/25

N2 - 3D reconstruction and digital double staining offer pathologists many new insights into tissue structure and metabolism. Key to these applications is the precise registration of histological slide images, that is challenging in several ways. One major challenge are differently stained slides, that highlight different parts of the tissue. In this paper we introduce a new registration method to face this multimodality. It abstracts the image information to cell nuclei densities. By minimizing the distance of these densities an affine transformation is determined that restores the lost spatial correspondences. The proposed density based registration is evaluated using consecutive histological slides. It is compared to a Mutual Information based registration and shown to be more accurate and robust.

AB - 3D reconstruction and digital double staining offer pathologists many new insights into tissue structure and metabolism. Key to these applications is the precise registration of histological slide images, that is challenging in several ways. One major challenge are differently stained slides, that highlight different parts of the tissue. In this paper we introduce a new registration method to face this multimodality. It abstracts the image information to cell nuclei densities. By minimizing the distance of these densities an affine transformation is determined that restores the lost spatial correspondences. The proposed density based registration is evaluated using consecutive histological slides. It is compared to a Mutual Information based registration and shown to be more accurate and robust.

UR - https://www.researchgate.net/publication/302285921_Multimodal_Image_Registration_in_Digital_Pathology_Using_Cell_Nuclei_Densities

U2 - 10.1007/978-3-662-46224-9_43

DO - 10.1007/978-3-662-46224-9_43

M3 - Conference contribution

SN - 978-3-662-46223-2

T3 - Informatik aktuell

SP - 245

BT - Bildverarbeitung für die Medizin 2015

A2 - Handels, Heinz

A2 - Deserno, Thomas M.

A2 - Meinzer, Hans-Peter

A2 - Tolxdorff, Thomas

PB - Springer Vieweg, Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - Workshop on Bildverarbeitung fur die Medizin 2015

Y2 - 15 March 2015 through 17 March 2015

ER -

Multimodal Image Registration in Digital Pathology Using Cell Nuclei Densities

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this