Unsupervised Method to Localize Masses in Mammograms
Breast cancer is one of the most prevalent types of cancer that mainly affects the women population. chances of effective treatment increase with early diagnosis. Mammography is considered one of the effective and proven techniques for the early diagnosis of breast cancer. Tissues around masses look...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9474494/ |
id |
doaj-5c67bb0dadfe47829c9db178b2d0d2e4 |
---|---|
record_format |
Article |
spelling |
doaj-5c67bb0dadfe47829c9db178b2d0d2e42021-07-19T23:00:11ZengIEEEIEEE Access2169-35362021-01-019993279933810.1109/ACCESS.2021.30947689474494Unsupervised Method to Localize Masses in MammogramsSajida Imran0https://orcid.org/0000-0001-7648-8442Bilal Ahmed Lodhi1https://orcid.org/0000-0003-4057-6859Ali Alzahrani2https://orcid.org/0000-0001-9501-8331Department of Computer Engineering, King Faisal University, Al-Ahsa, Saudi ArabiaSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast, U.K.Department of Computer Engineering, King Faisal University, Al-Ahsa, Saudi ArabiaBreast cancer is one of the most prevalent types of cancer that mainly affects the women population. chances of effective treatment increase with early diagnosis. Mammography is considered one of the effective and proven techniques for the early diagnosis of breast cancer. Tissues around masses look identical in a mammogram, which makes the automatic detection process a very challenging task; they are indistinguishable from the surrounding parenchyma. In this paper, we present an efficient and automated approach to segment masses in mammograms. The proposed method uses hierarchical clustering to isolate the salient area followed by extraction of features to reject false detection. We applied our method to two popular publicly available datasets (mini-MIAS and DDSM). A total of 56 images from the mini-mias database and 76 images from DDSM were randomly selected. Results are explained in terms of ROC (Receiver Operating Characteristics) curves and compared with other state-of-the-art techniques. Experimental results demonstrate the efficiency and advantages of the proposed system in automatic mass identification in mammograms.https://ieeexplore.ieee.org/document/9474494/Breast mass detectionautomatic mammogram segmentationmass classification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sajida Imran Bilal Ahmed Lodhi Ali Alzahrani |
spellingShingle |
Sajida Imran Bilal Ahmed Lodhi Ali Alzahrani Unsupervised Method to Localize Masses in Mammograms IEEE Access Breast mass detection automatic mammogram segmentation mass classification |
author_facet |
Sajida Imran Bilal Ahmed Lodhi Ali Alzahrani |
author_sort |
Sajida Imran |
title |
Unsupervised Method to Localize Masses in Mammograms |
title_short |
Unsupervised Method to Localize Masses in Mammograms |
title_full |
Unsupervised Method to Localize Masses in Mammograms |
title_fullStr |
Unsupervised Method to Localize Masses in Mammograms |
title_full_unstemmed |
Unsupervised Method to Localize Masses in Mammograms |
title_sort |
unsupervised method to localize masses in mammograms |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
Breast cancer is one of the most prevalent types of cancer that mainly affects the women population. chances of effective treatment increase with early diagnosis. Mammography is considered one of the effective and proven techniques for the early diagnosis of breast cancer. Tissues around masses look identical in a mammogram, which makes the automatic detection process a very challenging task; they are indistinguishable from the surrounding parenchyma. In this paper, we present an efficient and automated approach to segment masses in mammograms. The proposed method uses hierarchical clustering to isolate the salient area followed by extraction of features to reject false detection. We applied our method to two popular publicly available datasets (mini-MIAS and DDSM). A total of 56 images from the mini-mias database and 76 images from DDSM were randomly selected. Results are explained in terms of ROC (Receiver Operating Characteristics) curves and compared with other state-of-the-art techniques. Experimental results demonstrate the efficiency and advantages of the proposed system in automatic mass identification in mammograms. |
topic |
Breast mass detection automatic mammogram segmentation mass classification |
url |
https://ieeexplore.ieee.org/document/9474494/ |
work_keys_str_mv |
AT sajidaimran unsupervisedmethodtolocalizemassesinmammograms AT bilalahmedlodhi unsupervisedmethodtolocalizemassesinmammograms AT alialzahrani unsupervisedmethodtolocalizemassesinmammograms |
_version_ |
1721294404998660096 |