Automated detection of abnormal masses in ultrasound images. (4th February 2008)

• Record Type: Journal Article
• Authors: Poonguzhali, S.; Ravindran, G.
• Is Part Of: International journal of biomedical engineering and technology. Volume 1:Number 3(2008)
• Page Start: 250
• Page End: 258
• Publication Date: 2008-02-04
• Subjects: ultrasound images -- image segmentation -- seed point -- region growing -- texture analysis -- automated detection -- abnormal masses -- medical imaging -- cyst tumours -- liver tumours -- biomedical technology -- diagnostic ultrasound; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

The main aim of this work is to develop an automatic algorithm to identify the boundaries of abnormal regions in the ultrasound images, which is unique challenge in medical image segmentation. The initial seed point and the threshold to control the region growing process are automatically selected from the image and the feature-based region-growing algorithm is adopted. This method has been tested on different types of masses such as cyst and liver tumours. The result shows that the proposed algorithm is efficient in segmenting the region of interest without manual intervention. This work may help the physicians and radiologist to find the boundary of the abnormal regions from the ultrasound images.