Assessing tumour vascularity with 3D contrast-enhanced ultrasound: a new semi-automated segmentation framework

Authors:
A. Gasnier;R. Ardon;C. Ciofolo-Veit;E. Leen;J. M. Correas
Affiliations:
Philips Medical Systems Research Paris, Suresnes, France and Imaging Sciences Department, Imperial College, London, UK;Philips Medical Systems Research Paris, Suresnes, France;Philips Medical Systems Research Paris, Suresnes, France;Imaging Sciences Department, Imperial College, London, UK;Department of Adult Radiology, Necker Hospital, Paris, France
Venue:
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Year:
2010

Citing 2
Cited 0

Fuzzy region competition: a convex two-phase segmentation framework

SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Histogram based segmentation using Wasserstein distances

SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

3D contrast-enhanced ultrasound (CEUS) is a powerful imaging technique for tumour vascularity assessment, which is critical for radio-frequency ablation (RFA) planning or for the assessment of response to antiangiogenic therapies. In this paper, we propose a novel semi-automated method for the quantification of tumour vascularity in 3D CEUS data. We apply a two-step framework combining an interactive segmentation of the tumour necrosis followed by an automatic detection of the vascularity based on implicit representations. Experimental results on 3D CEUS images of renal cell carcinomas (RCC) show that our method is promising in terms of speed and quality.