files/journal/2022-09-02_12-54-44-000000_354.png

Journal of Engineering and Applied Sciences

ISSN: Online 1818-7803
ISSN: Print 1816-949x
134
Views
0
Downloads

Employing Symmetry Concept and Unsupervised Neural Network to Detect Abnormal Regions in IR Breast Thermograms

Rabab Saadoon Abdoon
Page: 898-907 | Received 21 Sep 2022, Published online: 21 Sep 2022

Full Text Reference XML File PDF File

Abstract

Infrared thermography is one of many medical scanning for detecting breast cancer and other abnormalities. Women breasts possess a high degree of symmetry, this property is employed in this research to detect the presence of abnormalities in breast front view thermograms of left and right breasts by proposing symmetry line algorithm. Clustering process utilizing unsupervised Self Organization Feature Map (SOFM) neural network is a second proposed technique in this work to isolate and extract abnormal regions in IR breast thermograms. The results declared the efficiency of the proposed symmetry line algorithm, depending on the histogram and standard deviation calculated values to detect breast abnormalities in the experimental thermograms. As well as the results of the second proposed unsupervised neural network clustering method proved its effective and adequate performance, it succeeded to extract the cancer and other abnormal regions in the abnormal sets of breast thermograms.


How to cite this article:

Rabab Saadoon Abdoon. Employing Symmetry Concept and Unsupervised Neural Network to Detect Abnormal Regions in IR Breast Thermograms.
DOI: https://doi.org/10.36478/jeasci.2020.898.907
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2020.898.907