A trichotomie technique to separate overlapped nuclei in microscopic cancer images

Chastine Fatichah; Abdullah M. Iliyasu; Ahmed S. Salama

doi:10.1109/SAI.2016.7555997

A trichotomie technique to separate overlapped nuclei in microscopic cancer images

Chastine Fatichah
, Abdullah M. Iliyasu
, Ahmed S. Salama

Electrical Engineering

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

2 Scopus citations

Abstract

Ability to clearly delineate the nuclei of microscopic cancer cells is crucial to the accuracy and efficiency of image-based approaches to cancer diagnosis and treatment. Oftentimes, however, such cells contain overlapped (or touched) nuclei. The study proposed in this work presents a hybrid trichotomic technique that combines the Gram-Schmidt method (GSM), handling of relevant geometric features of the cell nuclei, and application of the K-means clustering algorithm to segment, detect, and separate touched nuclei in microscopic cancer images. Using a dataset of microscopic images from two datasets comprising of breast cancer cells and acute lymphoblastic leukemia the proposed technique achieves average mean square error (MSE) of 0.087 and 0.075 for the two datatypes, respectively. Utilising the K-means clustering algorithm in the separation phase of the proposed technique ensures an average normalized accuracy of 0.73 and 0.91 respectively in terms of the nuclei separation for the microscopic breast cancer and acute lymphocyte leukemia cell images in comparison to manual approaches.

Original language	English
Title of host publication	Proceedings of 2016 SAI Computing Conference, SAI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	295-301
Number of pages	7
ISBN (Electronic)	9781467384605
DOIs	https://doi.org/10.1109/SAI.2016.7555997
State	Published - 29 Aug 2016
Event	2016 SAI Computing Conference, SAI 2016 - London, United Kingdom Duration: 13 Jul 2016 → 15 Jul 2016

Publication series

Name	Proceedings of 2016 SAI Computing Conference, SAI 2016

Conference

Conference	2016 SAI Computing Conference, SAI 2016
Country/Territory	United Kingdom
City	London
Period	13/07/16 → 15/07/16

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

disease diagnosis
Gram-Schmidt method
K-Means clustering algorithm
medical image processing
microscopic cancer images
nuclei segmentation
touched nuclei detection

Access to Document

10.1109/SAI.2016.7555997

Cite this

Fatichah, C., Iliyasu, A. M., & Salama, A. S. (2016). A trichotomie technique to separate overlapped nuclei in microscopic cancer images. In Proceedings of 2016 SAI Computing Conference, SAI 2016 (pp. 295-301). Article 7555997 (Proceedings of 2016 SAI Computing Conference, SAI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SAI.2016.7555997

@inproceedings{0126a855cb9d4508b129a7d485d34c24,

title = "A trichotomie technique to separate overlapped nuclei in microscopic cancer images",

abstract = "Ability to clearly delineate the nuclei of microscopic cancer cells is crucial to the accuracy and efficiency of image-based approaches to cancer diagnosis and treatment. Oftentimes, however, such cells contain overlapped (or touched) nuclei. The study proposed in this work presents a hybrid trichotomic technique that combines the Gram-Schmidt method (GSM), handling of relevant geometric features of the cell nuclei, and application of the K-means clustering algorithm to segment, detect, and separate touched nuclei in microscopic cancer images. Using a dataset of microscopic images from two datasets comprising of breast cancer cells and acute lymphoblastic leukemia the proposed technique achieves average mean square error (MSE) of 0.087 and 0.075 for the two datatypes, respectively. Utilising the K-means clustering algorithm in the separation phase of the proposed technique ensures an average normalized accuracy of 0.73 and 0.91 respectively in terms of the nuclei separation for the microscopic breast cancer and acute lymphocyte leukemia cell images in comparison to manual approaches.",

keywords = "disease diagnosis, Gram-Schmidt method, K-Means clustering algorithm, medical image processing, microscopic cancer images, nuclei segmentation, touched nuclei detection",

author = "Chastine Fatichah and Iliyasu, \{Abdullah M.\} and Salama, \{Ahmed S.\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 SAI Computing Conference, SAI 2016 ; Conference date: 13-07-2016 Through 15-07-2016",

year = "2016",

month = aug,

day = "29",

doi = "10.1109/SAI.2016.7555997",

language = "English",

series = "Proceedings of 2016 SAI Computing Conference, SAI 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "295--301",

booktitle = "Proceedings of 2016 SAI Computing Conference, SAI 2016",

address = "United States",

}

Fatichah, C, Iliyasu, AM & Salama, AS 2016, A trichotomie technique to separate overlapped nuclei in microscopic cancer images. in Proceedings of 2016 SAI Computing Conference, SAI 2016., 7555997, Proceedings of 2016 SAI Computing Conference, SAI 2016, Institute of Electrical and Electronics Engineers Inc., pp. 295-301, 2016 SAI Computing Conference, SAI 2016, London, United Kingdom, 13/07/16. https://doi.org/10.1109/SAI.2016.7555997

A trichotomie technique to separate overlapped nuclei in microscopic cancer images. / Fatichah, Chastine; Iliyasu, Abdullah M.; Salama, Ahmed S.
Proceedings of 2016 SAI Computing Conference, SAI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 295-301 7555997 (Proceedings of 2016 SAI Computing Conference, SAI 2016).

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

TY - GEN

T1 - A trichotomie technique to separate overlapped nuclei in microscopic cancer images

AU - Fatichah, Chastine

AU - Iliyasu, Abdullah M.

AU - Salama, Ahmed S.

PY - 2016/8/29

Y1 - 2016/8/29

N2 - Ability to clearly delineate the nuclei of microscopic cancer cells is crucial to the accuracy and efficiency of image-based approaches to cancer diagnosis and treatment. Oftentimes, however, such cells contain overlapped (or touched) nuclei. The study proposed in this work presents a hybrid trichotomic technique that combines the Gram-Schmidt method (GSM), handling of relevant geometric features of the cell nuclei, and application of the K-means clustering algorithm to segment, detect, and separate touched nuclei in microscopic cancer images. Using a dataset of microscopic images from two datasets comprising of breast cancer cells and acute lymphoblastic leukemia the proposed technique achieves average mean square error (MSE) of 0.087 and 0.075 for the two datatypes, respectively. Utilising the K-means clustering algorithm in the separation phase of the proposed technique ensures an average normalized accuracy of 0.73 and 0.91 respectively in terms of the nuclei separation for the microscopic breast cancer and acute lymphocyte leukemia cell images in comparison to manual approaches.

AB - Ability to clearly delineate the nuclei of microscopic cancer cells is crucial to the accuracy and efficiency of image-based approaches to cancer diagnosis and treatment. Oftentimes, however, such cells contain overlapped (or touched) nuclei. The study proposed in this work presents a hybrid trichotomic technique that combines the Gram-Schmidt method (GSM), handling of relevant geometric features of the cell nuclei, and application of the K-means clustering algorithm to segment, detect, and separate touched nuclei in microscopic cancer images. Using a dataset of microscopic images from two datasets comprising of breast cancer cells and acute lymphoblastic leukemia the proposed technique achieves average mean square error (MSE) of 0.087 and 0.075 for the two datatypes, respectively. Utilising the K-means clustering algorithm in the separation phase of the proposed technique ensures an average normalized accuracy of 0.73 and 0.91 respectively in terms of the nuclei separation for the microscopic breast cancer and acute lymphocyte leukemia cell images in comparison to manual approaches.

KW - disease diagnosis

KW - Gram-Schmidt method

KW - K-Means clustering algorithm

KW - medical image processing

KW - microscopic cancer images

KW - nuclei segmentation

KW - touched nuclei detection

UR - https://www.scopus.com/pages/publications/84988884802

U2 - 10.1109/SAI.2016.7555997

DO - 10.1109/SAI.2016.7555997

M3 - Conference contribution

AN - SCOPUS:84988884802

T3 - Proceedings of 2016 SAI Computing Conference, SAI 2016

SP - 295

EP - 301

BT - Proceedings of 2016 SAI Computing Conference, SAI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 SAI Computing Conference, SAI 2016

Y2 - 13 July 2016 through 15 July 2016

ER -

A trichotomie technique to separate overlapped nuclei in microscopic cancer images

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this