Mitosis detection from histological images using handcrafted features and artificial neural network

Hanan Hussain; Omar Hujran; K. P. Nitha

doi:10.1504/IJCAET.2022.120817

Mitosis detection from histological images using handcrafted features and artificial neural network

Hanan Hussain, Omar Hujran, K. P. Nitha

Department of Analytics in the Digital Era

Research output: Contribution to journal › Article › peer-review

Abstract

Mitosis is defined as the rapid division of cells and its count is relevant to predict the grading of breast cancer. Since manual mitosis detection is time consuming and prone to errors, a fast and accurate detection approach is proposed using handcrafted features with artificial neural network (ANN). This method includes three steps: 1) image pre-processing involves conversion on RGB image to red-channel; 2) segmentation which is done using fuzzy C-means clustering and handcrafted features are extracted; 3) classification in which both random forest classifier and ANN are ensemble to predict the outcome. The system was tested with Mitos-Atypia14 dataset and an accuracy of 91.6% is obtained.

Original language	English
Pages (from-to)	240-256
Number of pages	17
Journal	International Journal of Computer Aided Engineering and Technology
Volume	16
Issue number	2
DOIs	https://doi.org/10.1504/IJCAET.2022.120817
Publication status	Published - 2022

Keywords

ANN
Artificial neural network
Breast cancer detection
Mitosis detection
Random forest classifier

ASJC Scopus subject areas

Software
Engineering(all)
Computer Science Applications

UN SDGs

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

Access to Document

10.1504/IJCAET.2022.120817

Cite this

@article{fa903ed205564b0c84039dd2c8ae2d38,

title = "Mitosis detection from histological images using handcrafted features and artificial neural network",

abstract = "Mitosis is defined as the rapid division of cells and its count is relevant to predict the grading of breast cancer. Since manual mitosis detection is time consuming and prone to errors, a fast and accurate detection approach is proposed using handcrafted features with artificial neural network (ANN). This method includes three steps: 1) image pre-processing involves conversion on RGB image to red-channel; 2) segmentation which is done using fuzzy C-means clustering and handcrafted features are extracted; 3) classification in which both random forest classifier and ANN are ensemble to predict the outcome. The system was tested with Mitos-Atypia14 dataset and an accuracy of 91.6% is obtained.",

keywords = "ANN, Artificial neural network, Breast cancer detection, Mitosis detection, Random forest classifier",

author = "Hanan Hussain and Omar Hujran and Nitha, {K. P.}",

note = "Publisher Copyright: {\textcopyright} 2022 Inderscience Enterprises Ltd.",

year = "2022",

doi = "10.1504/IJCAET.2022.120817",

language = "English",

volume = "16",

pages = "240--256",

journal = "International Journal of Computer Aided Engineering and Technology",

issn = "1757-2657",

publisher = "Inderscience Publishers",

number = "2",

}

TY - JOUR

T1 - Mitosis detection from histological images using handcrafted features and artificial neural network

AU - Hussain, Hanan

AU - Hujran, Omar

AU - Nitha, K. P.

PY - 2022

Y1 - 2022

N2 - Mitosis is defined as the rapid division of cells and its count is relevant to predict the grading of breast cancer. Since manual mitosis detection is time consuming and prone to errors, a fast and accurate detection approach is proposed using handcrafted features with artificial neural network (ANN). This method includes three steps: 1) image pre-processing involves conversion on RGB image to red-channel; 2) segmentation which is done using fuzzy C-means clustering and handcrafted features are extracted; 3) classification in which both random forest classifier and ANN are ensemble to predict the outcome. The system was tested with Mitos-Atypia14 dataset and an accuracy of 91.6% is obtained.

AB - Mitosis is defined as the rapid division of cells and its count is relevant to predict the grading of breast cancer. Since manual mitosis detection is time consuming and prone to errors, a fast and accurate detection approach is proposed using handcrafted features with artificial neural network (ANN). This method includes three steps: 1) image pre-processing involves conversion on RGB image to red-channel; 2) segmentation which is done using fuzzy C-means clustering and handcrafted features are extracted; 3) classification in which both random forest classifier and ANN are ensemble to predict the outcome. The system was tested with Mitos-Atypia14 dataset and an accuracy of 91.6% is obtained.

KW - ANN

KW - Artificial neural network

KW - Breast cancer detection

KW - Mitosis detection

KW - Random forest classifier

UR - http://www.scopus.com/inward/record.url?scp=85124823700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85124823700&partnerID=8YFLogxK

U2 - 10.1504/IJCAET.2022.120817

DO - 10.1504/IJCAET.2022.120817

M3 - Article

AN - SCOPUS:85124823700

SN - 1757-2657

VL - 16

SP - 240

EP - 256

JO - International Journal of Computer Aided Engineering and Technology

JF - International Journal of Computer Aided Engineering and Technology

IS - 2

ER -

Mitosis detection from histological images using handcrafted features and artificial neural network

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this