Model-based Correction of Segmentation Errors in Digitised Histological Images

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Standard

Model-based Correction of Segmentation Errors in Digitised Histological Images. / Randell, David; Galton, Antony; Fouad, Shereen; Mehanna, Hesham; Landini, Gabriel.

Medical image understanding and analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings. Springer, 2017. p. 718-730 (Communications in computer and information science; Vol. 723).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Harvard

Randell, D, Galton, A, Fouad, S, Mehanna, H & Landini, G 2017, Model-based Correction of Segmentation Errors in Digitised Histological Images. in Medical image understanding and analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings. Communications in computer and information science, vol. 723, Springer, pp. 718-730, Medical Image Understanding and Analysis (MIUA) 2017, United Kingdom, 11/07/17. https://doi.org/10.1007/978-3-319-60964-5_63

APA

Randell, D., Galton, A., Fouad, S., Mehanna, H., & Landini, G. (2017). Model-based Correction of Segmentation Errors in Digitised Histological Images. In Medical image understanding and analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings (pp. 718-730). (Communications in computer and information science; Vol. 723). Springer. https://doi.org/10.1007/978-3-319-60964-5_63

Vancouver

Randell D, Galton A, Fouad S, Mehanna H, Landini G. Model-based Correction of Segmentation Errors in Digitised Histological Images. In Medical image understanding and analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings. Springer. 2017. p. 718-730. (Communications in computer and information science). https://doi.org/10.1007/978-3-319-60964-5_63

Author

Randell, David ; Galton, Antony ; Fouad, Shereen ; Mehanna, Hesham ; Landini, Gabriel. / Model-based Correction of Segmentation Errors in Digitised Histological Images. Medical image understanding and analysis: 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings. Springer, 2017. pp. 718-730 (Communications in computer and information science).

Bibtex

@inproceedings{8f0b52914a20432daa833bc7211fe09a,
title = "Model-based Correction of Segmentation Errors in Digitised Histological Images",
abstract = "This paper describes an application of model-based methods for the algorithmic correction of segmentation errors in digitised histo- logical images. This is a real-world application where qualitative spatial reasoning and constraint-satisfaction programming methods have been integrated with classical image processing methods to develop context- based histological imaging algorithms. The context here arises from: (i) making an ontological stand whereby regions rather than pixels in digi- tised images are deemed to be the main carriers of histological content, and (ii) highlighting the importance of and explicitly modelling topo- logical (and in particular relational) information encoded in digitised histological images. The topological analysis and representational frame- work used is provided by the spatial logic Discrete Meterotopology. We use this to augment classical Mathematical Morphology pixel and region- based operations by explicitly encoding sets of binary relations on pairs of regions such as contact, overlap and the part-whole relation. These mereotopological relations are used both to model the domain and to guide resegmentation algorithms so that our interpreted images conform to the requirements for a valid histological model. ",
keywords = "Histological Image Processing, Mereotopology, Graph Theory",
author = "David Randell and Antony Galton and Shereen Fouad and Hesham Mehanna and Gabriel Landini",
year = "2017",
doi = "10.1007/978-3-319-60964-5_63",
language = "English",
isbn = "978-3-319-60963-8",
series = "Communications in computer and information science",
publisher = "Springer",
pages = " 718--730",
booktitle = "Medical image understanding and analysis",
note = "Medical Image Understanding and Analysis (MIUA) 2017 ; Conference date: 11-07-2017 Through 13-07-2017",
url = "https://miua2017.wordpress.com/",

}

RIS

TY - GEN

T1 - Model-based Correction of Segmentation Errors in Digitised Histological Images

AU - Randell, David

AU - Galton, Antony

AU - Fouad, Shereen

AU - Mehanna, Hesham

AU - Landini, Gabriel

PY - 2017

Y1 - 2017

N2 - This paper describes an application of model-based methods for the algorithmic correction of segmentation errors in digitised histo- logical images. This is a real-world application where qualitative spatial reasoning and constraint-satisfaction programming methods have been integrated with classical image processing methods to develop context- based histological imaging algorithms. The context here arises from: (i) making an ontological stand whereby regions rather than pixels in digi- tised images are deemed to be the main carriers of histological content, and (ii) highlighting the importance of and explicitly modelling topo- logical (and in particular relational) information encoded in digitised histological images. The topological analysis and representational frame- work used is provided by the spatial logic Discrete Meterotopology. We use this to augment classical Mathematical Morphology pixel and region- based operations by explicitly encoding sets of binary relations on pairs of regions such as contact, overlap and the part-whole relation. These mereotopological relations are used both to model the domain and to guide resegmentation algorithms so that our interpreted images conform to the requirements for a valid histological model.

AB - This paper describes an application of model-based methods for the algorithmic correction of segmentation errors in digitised histo- logical images. This is a real-world application where qualitative spatial reasoning and constraint-satisfaction programming methods have been integrated with classical image processing methods to develop context- based histological imaging algorithms. The context here arises from: (i) making an ontological stand whereby regions rather than pixels in digi- tised images are deemed to be the main carriers of histological content, and (ii) highlighting the importance of and explicitly modelling topo- logical (and in particular relational) information encoded in digitised histological images. The topological analysis and representational frame- work used is provided by the spatial logic Discrete Meterotopology. We use this to augment classical Mathematical Morphology pixel and region- based operations by explicitly encoding sets of binary relations on pairs of regions such as contact, overlap and the part-whole relation. These mereotopological relations are used both to model the domain and to guide resegmentation algorithms so that our interpreted images conform to the requirements for a valid histological model.

KW - Histological Image Processing

KW - Mereotopology

KW - Graph Theory

U2 - 10.1007/978-3-319-60964-5_63

DO - 10.1007/978-3-319-60964-5_63

M3 - Conference contribution

SN - 978-3-319-60963-8

T3 - Communications in computer and information science

SP - 718

EP - 730

BT - Medical image understanding and analysis

PB - Springer

T2 - Medical Image Understanding and Analysis (MIUA) 2017

Y2 - 11 July 2017 through 13 July 2017

ER -