Detection of breast abnormalities of thermograms based on a new segmentation method

Ali, MAS, Sayed, GI, Gaber, T ORCID: https://orcid.org/0000-0003-4065-4191, Hassanien, AE, Snasel, V and Silva, LF 2015, Detection of breast abnormalities of thermograms based on a new segmentation method , in: Federated Conference on Computer Science and Information System.

[img] PDF - Accepted Version
Restricted to Repository staff only

Download (485kB)

Abstract

Breast cancer is one from various diseases that has got great attention in the last decades. This due to the number of women who died because of this disease. Segmentation is always an important step in developing a CAD system. This paper proposed an automatic segmentation method for the Region of Interest (ROI) from breast thermograms. This method is based on the data acquisition protocol parameter (the distance from the patient to the camera) and the image statistics of DMR-IR database. To evaluated the results of this method, an approach for the detection of breast abnormalities of thermograms was also proposed. Statistical and texture features from the segmented ROI were extracted and the SVM with its kernel function was used to detect the normal and abnormal breasts based on these features. The experimental results, using the benchmark database, DMR-IR, shown that the classification accuracy reached (100%). Also, using the measurements of the recall and the precision, the classification results reached 100%. This means that the proposed segmentation method is a promising technique for extracting the ROI of breast thermograms.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre
Journal or Publication Title: Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, FedCSIS 2015
Publisher: ACSIS
Related URLs:
Funders: European Social Fund, The state budget of the Czech Republic
Depositing User: Dr. Tarek Gaber
Date Deposited: 11 Sep 2019 11:02
Last Modified: 11 Sep 2019 11:15
URI: http://usir.salford.ac.uk/id/eprint/52097

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year