scholarly journals Automatic detection of regions of interest in breast ultrasound images based on local phase information

2015 ◽  
Vol 26 (s1) ◽  
pp. S1265-S1273 ◽  
Author(s):  
Xin Wang ◽  
Yi Guo ◽  
Yuanyuan Wang
Keyword(s):  
Automatic Detection ◽  
Breast Ultrasound ◽  
Regions Of Interest ◽  
Ultrasound Images ◽  
Local Phase ◽  
Phase Information

scholarly journals A Preprocess Method of External Disturbance Suppression for Carotid Wall Motion Estimation Using Local Phase and Orientation of B-Mode Ultrasound Sequences

2019 ◽  
Vol 2019 ◽  
pp. 1-15
Author(s):  
Qinghui Zhang ◽  
Junqiu Li ◽  
Zhenping Qiang ◽  
Libo He
Keyword(s):  
Motion Estimation ◽  
Wall Motion ◽  
Structural Information ◽  
External Disturbance ◽  
Estimation Accuracy ◽  
Ultrasound Images ◽  
Local Phase ◽  
Registration Method ◽  
Anisotropic Diffusion Filter ◽  
Disturbance Suppression

Estimating the motions of the common carotid artery wall plays a very important role in early diagnosis of the carotid atherosclerotic disease. However, the disturbances caused by either the instability of the probe operator or the breathing of subjects degrade the estimation accuracy of arterial wall motion when performing speckle tracking on the B-mode ultrasound images. In this paper, we propose a global registration method to suppress external disturbances before motion estimation. The local vector images, transformed from B-mode images, were used for registration. To take advantage of both the structural information from the local phase and the geometric information from the local orientation, we proposed a confidence coefficient to combine them two. Furthermore, we altered the speckle reducing anisotropic diffusion filter to improve the performance of disturbance suppression. We compared this method with schemes of extracting wall displacement directly from B-mode or phase images. The results show that this scheme can effectively suppress the disturbances and significantly improve the estimation accuracy.

Nipple Localization in Automated Whole Breast Ultrasound Coronal Scans Using Ensemble Learning

2020 ◽  
Vol 43 (1) ◽  
pp. 29-45
Author(s):  
Alex Noel Joseph Raj ◽  
Ruban Nersisson ◽  
Vijayalakshmi G. V. Mahesh ◽  
Zhemin Zhuang
Keyword(s):  
Texture Features ◽  
Breast Ultrasound ◽  
Support Vector ◽  
Ultrasound Images ◽  
Shadow Area ◽  
Hu Moments ◽  
Artificial Neural Network Ann ◽  
Cade System ◽  
Occurrence Matrix ◽  
Shape Complexity

Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patients. The test results show that the proposed CADe system achieves 91.99% accuracy, 97.55% specificity, 82.46% sensitivity and 88% F-score on our dataset.

Automatic superpixel-based segmentation method for breast ultrasound images

2019 ◽  
Vol 121 ◽  
pp. 78-96 ◽  
Author(s):  
Mohammad I. Daoud ◽  
Ayman A. Atallah ◽  
Falah Awwad ◽  
Mahasen Al-Najjar ◽  
Rami Alazrai
Keyword(s):  
Breast Ultrasound ◽  
Ultrasound Images ◽  
Segmentation Method
Sign in / Sign up

Export Citation Format

Share Document