Morphological separation of clustered nuclei in histological images

Shereen Fouad; Gabriel Landini; David Randell; Antony Galton

doi:10.1007/978-3-319-41501-7_67

Morphological separation of clustered nuclei in histological images

Shereen Fouad, Gabriel Landini, David Randell, Antony Galton

Dentistry

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

3 Citations (Scopus)

148 Downloads (Pure)

Abstract

Automated nuclear segmentation is essential in the analysis of most microscopy images. This paper presents a novel concavitybased method for the separation of clusters of nuclei in binary images. A heuristic rule, based on object size, is used to infer the existence of merged regions. Concavity extrema detected along the merged-cluster boundary are used to guide the separation of overlapping regions. Inner split contours of multiple concavities along the nuclear boundary are estimated via a series of morphological procedures. The algorithm was evaluated on images of H400 cells in monolayer cultures and compares favourably with the state-of-art watershed method commonly used to separate overlapping nuclei.

Original language	English
Title of host publication	13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings
Publisher	Springer
Pages	599-607
Volume	9730
ISBN (Electronic)	9783319415017
ISBN (Print)	9783319415000
DOIs	https://doi.org/10.1007/978-3-319-41501-7_67
Publication status	E-pub ahead of print - 1 Jul 2016
Event	13th International Conference on Image Analysis and Recognition - Póvoa de Varzim, Portugal Duration: 13 Jul 2016 → 15 Jul 2016

Publication series

Name	Lecture Notes in Computer Science
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	13th International Conference on Image Analysis and Recognition
Abbreviated title	ICIAR 2016
Country/Territory	Portugal
City	Póvoa de Varzim
Period	13/07/16 → 15/07/16

Keywords

Histological images
Nuclear segmentation
Mathematical morphology
Concavity analysis

Access to Document

10.1007/978-3-319-41501-7_67Licence: Creative Commons: Attribution (CC BY)

Fouad_et_al_Morphological_seperation_Image_analysis_and_recognition
Eligibility for repository: Checked on 20/7/2016. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-41501-7_67
Final published version, 317 KBLicence: Creative Commons: Attribution (CC BY)

Cite this

Fouad, S., Landini, G., Randell, D., & Galton, A. (2016). Morphological separation of clustered nuclei in histological images. In 13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings (Vol. 9730, pp. 599-607). (Lecture Notes in Computer Science). Springer. Advance online publication. https://doi.org/10.1007/978-3-319-41501-7_67

@inbook{922e7e2367564f59b9531edb7a146d67,

title = "Morphological separation of clustered nuclei in histological images",

abstract = "Automated nuclear segmentation is essential in the analysis of most microscopy images. This paper presents a novel concavitybased method for the separation of clusters of nuclei in binary images. A heuristic rule, based on object size, is used to infer the existence of merged regions. Concavity extrema detected along the merged-cluster boundary are used to guide the separation of overlapping regions. Inner split contours of multiple concavities along the nuclear boundary are estimated via a series of morphological procedures. The algorithm was evaluated on images of H400 cells in monolayer cultures and compares favourably with the state-of-art watershed method commonly used to separate overlapping nuclei. ",

keywords = "Histological images, Nuclear segmentation, Mathematical morphology, Concavity analysis",

author = "Shereen Fouad and Gabriel Landini and David Randell and Antony Galton",

year = "2016",

month = jul,

day = "1",

doi = "10.1007/978-3-319-41501-7_67",

language = "English",

isbn = "9783319415000",

volume = "9730",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "599--607",

booktitle = "13th International Conference on Image Analysis and Recognition, ICIAR 2016, P{\'o}voa de Varzim, Portugal, July 13-15, 2016. Proceedings",

note = "13th International Conference on Image Analysis and Recognition, ICIAR 2016 ; Conference date: 13-07-2016 Through 15-07-2016",

}

Fouad, S, Landini, G, Randell, D & Galton, A 2016, Morphological separation of clustered nuclei in histological images. in 13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings. vol. 9730, Lecture Notes in Computer Science, Springer, pp. 599-607, 13th International Conference on Image Analysis and Recognition, Póvoa de Varzim, Portugal, 13/07/16. https://doi.org/10.1007/978-3-319-41501-7_67

Morphological separation of clustered nuclei in histological images. / Fouad, Shereen; Landini, Gabriel; Randell, David et al.
13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings. Vol. 9730 Springer, 2016. p. 599-607 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - Morphological separation of clustered nuclei in histological images

AU - Fouad, Shereen

AU - Landini, Gabriel

AU - Randell, David

AU - Galton, Antony

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Automated nuclear segmentation is essential in the analysis of most microscopy images. This paper presents a novel concavitybased method for the separation of clusters of nuclei in binary images. A heuristic rule, based on object size, is used to infer the existence of merged regions. Concavity extrema detected along the merged-cluster boundary are used to guide the separation of overlapping regions. Inner split contours of multiple concavities along the nuclear boundary are estimated via a series of morphological procedures. The algorithm was evaluated on images of H400 cells in monolayer cultures and compares favourably with the state-of-art watershed method commonly used to separate overlapping nuclei.

AB - Automated nuclear segmentation is essential in the analysis of most microscopy images. This paper presents a novel concavitybased method for the separation of clusters of nuclei in binary images. A heuristic rule, based on object size, is used to infer the existence of merged regions. Concavity extrema detected along the merged-cluster boundary are used to guide the separation of overlapping regions. Inner split contours of multiple concavities along the nuclear boundary are estimated via a series of morphological procedures. The algorithm was evaluated on images of H400 cells in monolayer cultures and compares favourably with the state-of-art watershed method commonly used to separate overlapping nuclei.

KW - Histological images

KW - Nuclear segmentation

KW - Mathematical morphology

KW - Concavity analysis

U2 - 10.1007/978-3-319-41501-7_67

DO - 10.1007/978-3-319-41501-7_67

M3 - Chapter (peer-reviewed)

SN - 9783319415000

VL - 9730

T3 - Lecture Notes in Computer Science

SP - 599

EP - 607

BT - 13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings

PB - Springer

T2 - 13th International Conference on Image Analysis and Recognition

Y2 - 13 July 2016 through 15 July 2016

ER -

Fouad S, Landini G, Randell D, Galton A. Morphological separation of clustered nuclei in histological images. In 13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15, 2016. Proceedings. Vol. 9730. Springer. 2016. p. 599-607. (Lecture Notes in Computer Science). Epub 2016 Jul 1. doi: 10.1007/978-3-319-41501-7_67

Morphological separation of clustered nuclei in histological images

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this