Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images

Breast cancer is considered to be one of the most threatening issues in clinical practice. However, existing breast cancer diagnosis methods face questions of complexity, cost, human-dependency, and inaccuracy. Recently, many computerized and interdisciplinary systems have been developed to avoid hu...

Full description

Bibliographic Details
Main Authors: Mohammed, Mazin Abed, Al-Khateeb, Belal, Rashid, Ahmed Noori, Ahmed Ibrahim, Dheyaa, Abd Ghani, Mohd Khanapi, A. Mostafa, Salama
Format: Article
Language:English
Published: Elsevier 2018
Subjects:
Online Access:http://eprints.uthm.edu.my/5145/
http://eprints.uthm.edu.my/5145/1/AJ%202018%20%28848%29%20Neural%20network%20and%20multi-fractal%20dimension%20features%20for%20breast%20cancer%20classification%20from%20ultrasound%20images.pdf
_version_ 1848888476553969664
author Mohammed, Mazin Abed
Al-Khateeb, Belal
Rashid, Ahmed Noori
Ahmed Ibrahim, Dheyaa
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
author_facet Mohammed, Mazin Abed
Al-Khateeb, Belal
Rashid, Ahmed Noori
Ahmed Ibrahim, Dheyaa
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
author_sort Mohammed, Mazin Abed
building UTHM Institutional Repository
collection Online Access
description Breast cancer is considered to be one of the most threatening issues in clinical practice. However, existing breast cancer diagnosis methods face questions of complexity, cost, human-dependency, and inaccuracy. Recently, many computerized and interdisciplinary systems have been developed to avoid human errors in both quantification and diagnosis. A computerized system can be further improved to optimize the efficiency of breast tumour identification. The current paper presents an effort to automate characterization of breast cancer from ultrasound images using multi-fractal dimensions and backpropagation neural networks. In this study, a total of 184 breast ultrasound images (72 abnormal (tumour cases) and 112 normal cases) were examined. Various setups were employed to achieve a decent balance between positive and negative rates of the diagnosed cases. The obtained results manifested in high rates of precision (82.04%), sensitivity (79.39%), and specificity (84.75%).
first_indexed 2025-11-15T20:10:53Z
format Article
id uthm-5145
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:10:53Z
publishDate 2018
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling uthm-51452022-01-06T02:36:08Z http://eprints.uthm.edu.my/5145/ Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images Mohammed, Mazin Abed Al-Khateeb, Belal Rashid, Ahmed Noori Ahmed Ibrahim, Dheyaa Abd Ghani, Mohd Khanapi A. Mostafa, Salama QA76 Computer software TA Engineering (General). Civil engineering (General) TA168 Systems engineering Breast cancer is considered to be one of the most threatening issues in clinical practice. However, existing breast cancer diagnosis methods face questions of complexity, cost, human-dependency, and inaccuracy. Recently, many computerized and interdisciplinary systems have been developed to avoid human errors in both quantification and diagnosis. A computerized system can be further improved to optimize the efficiency of breast tumour identification. The current paper presents an effort to automate characterization of breast cancer from ultrasound images using multi-fractal dimensions and backpropagation neural networks. In this study, a total of 184 breast ultrasound images (72 abnormal (tumour cases) and 112 normal cases) were examined. Various setups were employed to achieve a decent balance between positive and negative rates of the diagnosed cases. The obtained results manifested in high rates of precision (82.04%), sensitivity (79.39%), and specificity (84.75%). Elsevier 2018 Article PeerReviewed text en http://eprints.uthm.edu.my/5145/1/AJ%202018%20%28848%29%20Neural%20network%20and%20multi-fractal%20dimension%20features%20for%20breast%20cancer%20classification%20from%20ultrasound%20images.pdf Mohammed, Mazin Abed and Al-Khateeb, Belal and Rashid, Ahmed Noori and Ahmed Ibrahim, Dheyaa and Abd Ghani, Mohd Khanapi and A. Mostafa, Salama (2018) Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images. Computers and Electrical Engineering, 70. pp. 871-882. ISSN 0045-7906
spellingShingle QA76 Computer software
TA Engineering (General). Civil engineering (General)
TA168 Systems engineering
Mohammed, Mazin Abed
Al-Khateeb, Belal
Rashid, Ahmed Noori
Ahmed Ibrahim, Dheyaa
Abd Ghani, Mohd Khanapi
A. Mostafa, Salama
Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title_full Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title_fullStr Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title_full_unstemmed Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title_short Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
title_sort neural network and multi-fractal dimension features for breast cancer classification from ultrasound images
topic QA76 Computer software
TA Engineering (General). Civil engineering (General)
TA168 Systems engineering
url http://eprints.uthm.edu.my/5145/
http://eprints.uthm.edu.my/5145/1/AJ%202018%20%28848%29%20Neural%20network%20and%20multi-fractal%20dimension%20features%20for%20breast%20cancer%20classification%20from%20ultrasound%20images.pdf