In this paper we describe a new approach for segmentation of liver from CT images and further the segmentation of liver vessels to create a visualization model for surgical purposes. Since usual approaches, based on density models or edge detection, don’t work well for liver, we investigate the texture of the liver to classify each pixel, whether it lies on the liver-background boundary or outside it. The classifier outputs the boundaries of the liver in each slice, which are used then to create the organ volume. Vessels are segmented then inside the liver volume using a single automatically selected threshold. The result is morphologically closed and smoothed by a Gaussian kernel then.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
M. Sonka and J. M. Fitzpatrick, Handbook of Medical Imaging: Medical Image Processing and Analysis (SPIE Society of Photo-Optical Instrumentation Engi, Bellingham, Washington, 2000), 0819436224.
M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine Vision, 3rd edition (Thomson Learning, Toronto, 2007), ISBN 049508252X.
The article is published in the original. This article uses the materials of the report submitted at the 8th Open German-Russian Workshop “Pattern Recognition and Image Understanding,” Nizhni Novgorod, November 21–26, 2011.
Petr Zimmermann received the MS degree from the University of West Bohemia in Pilsen (Czech Republic) in cybernetics in 2010. He is currently a PhD student at Faculty of Applied Sciences, Department of Cybernetics, Czech Republic. His research interests are image process-ing, medical image processing and SW development.
Ivan Pirner received the MS degree from the University of West Bohemia in Pilsen (Czech Republic) in cybernetics in 2010. He is currently a PhD student at Faculty of Applied Sciences, Department of Cybernetics, Czech Republic. His research interests are image processing, medical image processing and SW development.
Milos Zelezny was born in Plzen, Czech Republic, in 1971. He received his Ing. (=M.S.) and Ph.D. degrees in Cybernetics from the University of West Bohemia, Plzen, Czech Republic (UWB) in 1994 and in 2002 respectively. Since 2012 he is an associate professor at the UWB. He has been delivering lectures on Digital Image Processing, Structural Pattern Recognition and Remote Sensing since 1996 at UWB. He works on projects on multi modal human-computer speech interfaces (audio visual speech, gestures, sign language) and computer vision (medical and industrial imaging).
About this article
Cite this article
Zimmermann, P., Pirner, I. & Zelezny, M. Segmentation of liver vessels for surgical purposes. Pattern Recognit. Image Anal. 24, 185–187 (2014). https://doi.org/10.1134/S1054661814010210
- Medical image segmentation
- texture-based classification
- mathematical morphology