Breast ultrasound region of interest detection and lesion localisation

Computer-aid lesion detection and segmentation in breast ultrasound images

extremal region detection guided by maxima of gradient magnitude

a problem of computer vision applications is to detect regions of interest under dif- ferent imaging conditions. the state-of-the-art maximally stable extremal regions (mser) detects affine covariant regions by applying all possible thresholds on the input image, and through three main steps including: 1) making a component tree of extremal regions’ evolution (enumeration), 2) obtaining region ...

Fully automatic lesion boundary detection in ultrasound breast images

We propose a novel approach to fully automatic lesion boundary detection in ultrasound breast images. The novelty of the proposed work lies in the complete automation of the manual process of initial Region-of-Interest (ROI) labeling and in the procedure adopted for the subsequent lesion boundary detection. Histogram equalization is initially used to preprocess the images followed by hybrid fil...

Horizon Scanning Technology Horizon Scanning Report Intraoperative ultrasound for breast lesion localisation during breast conserving surgery (lumpectomy)

Assessment of Ultrasound / Radio-guided Occult Lesion Localization in Non-palpable Breast Lesions

Objective(s): Controversy exists about the localization of non-palpable breast lesions. In many countries, the gold standard for the diagnosis of these lesions is needle localization due to its accuracy. This study sought to compare the ultrasoundand radio-guided occult lesion localization (ROLL) as a simple method with the conventional procedures in terms of their diagnostic power. Methods: Th...