## Abstract Automated image analysis aims to extract relevant information from contrastโenhanced magnetic resonance images (CEโMRI) of the breast and improve the accuracy and consistency of image interpretation. In this work, we extend the traditional 2D grayโlevel coโoccurrence matrix (GLCM) metho
Texture analysis of lesions in breast ultrasound images
โ Scribed by Radhika Sivaramakrishna; Kimerly A. Powell; Michael L. Lieber; William A. Chilcote; Raj Shekhar
- Publisher
- Elsevier Science
- Year
- 2002
- Tongue
- English
- Weight
- 177 KB
- Volume
- 26
- Category
- Article
- ISSN
- 0895-6111
No coin nor oath required. For personal study only.
โฆ Synopsis
We investigate the use of Haralick's texture features and posterior acoustic attenuation descriptors (PAAD) for the characterization of ultrasound (US) breast lesions. 71 lesions (24 cyst, 21 benign solid mass and 26 malignant solid masses) were manually segmented on two-dimensional breast US images. 28 Haralick's descriptors and two PAAD were evaluated on these segmented lesions. Mean of Sum Average, Range of Sum Entropy and the second PAAD best discriminated cysts from noncysts. Range of Correlation and the second PAAD best discriminated solid malignant from benign lesions. Computerized analysis of breast US images can increase the specificity of breast sonography by providing a better characterization of solid lesions.
๐ SIMILAR VOLUMES
Ultrasound (US) phantoms are used to simulate the main acoustic properties of human soft tissues and are usually applied in guided biopsy training and equipment calibration. In this work it is presented an ultrasound phantom that mimics breast lesions with irregular edge, which is a typical feature
Intravascular Ultrasound (IVUS) is a diagnostic imaging technique that provides tomographic visualization of coronary arteries. The aim of this study was to evaluate five texture analysis techniques and determine their ability to distinguish between plaque lesions of different composition. Using his
## Abstract Texture analysis was applied to highโresolution, contrastโenhanced (CE) images of the breast to provide a method of lesion discrimination. Significant differences were seen between benign and malignant lesions for a number of textural features, including entropy and sum entropy. Using l