Open AccessRegion of Interest Segmentation Based on Clustering Techniques for Breast Cancer Ultrasound Images: A Review
Author(s) -
Muhammad Muhammad,
Diyar Qader Zeebaree,
Adnan Mohsin Abdulazeez Brifcani,
Jwan Najeeb Saeed,
Dilovan Asaad Zebari
Publication year - 2020
Publication title -
journal of applied science and technology trends
Language(s) - English
Resource type - Journals
ISSN - 2708-0757
DOI - 10.38094/jastt20201328
Subject(s) - speckle noise , segmentation , breast cancer , ultrasound , artificial intelligence , breast ultrasound , cluster analysis , computer science , speckle pattern , computer vision , focus (optics) , region of interest , noise (video) , medicine , radiology , cancer , image (mathematics) , mammography , physics , optics
The most prevalent cancer amongst women is woman breast cancer. Ultrasound imaging is a widely employed method for identifying and diagnosing breast abnormalities. Computer-aided diagnosis technologies have lately been developed with ultrasound images to help radiologists enhance the accuracy of the diagnosis. This paper presents several ultrasound image segmentation techniques, mainly focus on eight clustering methods over the last 10 years, and it shows the advantages and disadvantages of these approaches. Breast ultrasound image segmentation is, therefore, still an accessible and challenging issue due to numerous ultrasound artifacts introduced in the imaging process, including high speckle noise, poor contrast, blurry edges, weak signal-to-noise ratio, and intensity inhomogeneity.