Interactive Visual Analysis of Contrast-enhanced Ultrasound Databased on Small Neighborhood Statistics
Abstract
Contrast-enhanced ultrasound (CEUS) has recently become an important technology for lesion detection and characterization in cancer diagnosis. CEUS is used to investigate the perfusion kinetics in tissue over time, which relates to tissue vascularization. In this paper we present a pipeline that enables interactive visual exploration and semi-automatic segmentation and classification of CEUS data.For the visual analysis of this challenging data, with characteristic noise patterns and residual movements, we propose a robust method to derive expressive enhancement measures from small spatio-temporal neighborhoods. We use this information in a stagedvisual analysis pipeline that leads from a more local investigation to global results such as the delineation of anatomic regions according to their perfusion properties. To make the visual exploration interactive, we have developed an accelerated frameworkbased on the OpenCL library, that exploits modern many-cores hardware. Using our application, we were able to analyze datasets from CEUS liver examinations, being able to identify several focal liver lesions, segment and analyze them quickly and precisely, and eventually characterize them.
P. Angelelli, K. Nylund, O. H. Gilja, and H. Hauser, "Interactive Visual Analysis of Contrast-enhanced Ultrasound Databased on Small Neighborhood Statistics," Computers & Graphics - Special Issue on Visual Computing in Biology and Medicine, vol. 35, iss. 2, p. 218–226, 2011.
[BibTeX]
Contrast-enhanced ultrasound (CEUS) has recently become an important technology for lesion detection and characterization in cancer diagnosis. CEUS is used to investigate the perfusion kinetics in tissue over time, which relates to tissue vascularization. In this paper we present a pipeline that enables interactive visual exploration and semi-automatic segmentation and classification of CEUS data.For the visual analysis of this challenging data, with characteristic noise patterns and residual movements, we propose a robust method to derive expressive enhancement measures from small spatio-temporal neighborhoods. We use this information in a stagedvisual analysis pipeline that leads from a more local investigation to global results such as the delineation of anatomic regions according to their perfusion properties. To make the visual exploration interactive, we have developed an accelerated frameworkbased on the OpenCL library, that exploits modern many-cores hardware. Using our application, we were able to analyze datasets from CEUS liver examinations, being able to identify several focal liver lesions, segment and analyze them quickly and precisely, and eventually characterize them.
@ARTICLE {angelelli11ultrasoundStatistics,
author = "Paolo Angelelli and Kim Nylund and Odd Helge Gilja and Helwig Hauser",
title = "Interactive Visual Analysis of Contrast-enhanced Ultrasound Databased on Small Neighborhood Statistics",
journal = "Computers \& Graphics - Special Issue on Visual Computing in Biology and Medicine",
year = "2011",
volume = "35",
number = "2",
pages = "218--226",
abstract = "Contrast-enhanced ultrasound (CEUS) has recently become an important technology for lesion detection and characterization in cancer diagnosis. CEUS is used to investigate the perfusion kinetics in tissue over time, which relates to tissue vascularization. In this paper we present a pipeline that enables interactive visual exploration and semi-automatic segmentation and classification of CEUS data.For the visual analysis of this challenging data, with characteristic noise patterns and residual movements, we propose a robust method to derive expressive enhancement measures from small spatio-temporal neighborhoods. We use this information in a stagedvisual analysis pipeline that leads from a more local investigation to global results such as the delineation of anatomic regions according to their perfusion properties. To make the visual exploration interactive, we have developed an accelerated frameworkbased on the OpenCL library, that exploits modern many-cores hardware. Using our application, we were able to analyze datasets from CEUS liver examinations, being able to identify several focal liver lesions, segment and analyze them quickly and precisely, and eventually characterize them.",
pdf = "pdfs/angelelli11CEUSIVA.pdf",
vid = "vids/angelelli11CEUSSegmentation.wmv",
images = "images/angelelli11ultrasoundStatistics2.jpg, images/angelelli11ultrasoundStatistics1.jpg",
thumbnails = "images/angelelli11ultrasoundStatistics2_thumb.jpg, images/angelelli11ultrasoundStatistics1_thumb.jpg",
url = "//dx.doi.org/10.1016/j.cag.2010.12.005",
project = "illustrasound,medviz,illvis"
}