Optimized graph-based segmentation for ultrasound images

Segmentation of medical images is an inevitable image processing step for computer-aided diagnosis. Due to complex acoustic inferences and artifacts, accurate extraction of breast lesions in ultrasound images remains a challenge. Although there have been many segmentation techniques proposed, the performance often varies with different image data, leading to poor adaptability in real applications. Intelligent computing techniques for adaptively learning the boundaries of image objects are preferred. This paper focuses on optimization of a previously documented method called robust graph-based (RGB) segmentation algorithm to extract breast tumors in ultrasound images more adaptively and accurately. A novel technique named as parameter-automatically optimized robust graph-based (PAORGB) image segmentation method is accordingly proposed and performed on breast ultrasound images. A particle swarm optimization algorithm is incorporated with the RGB method to achieve optimal or approximately optimal parameters. Experimental results have shown that the proposed technique can more accurately segment lesions from ultrasound images compared to the RGB and two conventional region-based methods.