Multiscale Graph-Cut for 3D Segmentation of Compact Objects
The article is a step forward towards improving image segmentation using a popular method called Graph-Cut. We focus on optimizing the algorithm for processing data, in which the target object occupies only a small portion of the total volume. We propose a two-step procedure. At the first step, the location of the object is determined roughly. At the second step, Graph-Cut segmentation is performed with a special multi-scale chart structure. Two different graph construction methods are suggested. The calculation time of both variants is compared with the original Graph-Cut method. The msgc_lo2hi method has been shown to provide a statistically significant time reduction of the computational costs.
KeywordsGraph-Cut method Multiscale Medical imaging Image segmentation
This work has been supported by Charles University Research Centre program UNCE/MED/006 “University Center of Clinical and Experimental Liver Surgery” and Ministry of Education project ITI CZ.02.1.01/0.0/0.0/17_048/0007280: Application of modern technologies in medicine and industry and Erasmus+ project MedTrain3DModsim, nr. 2016-1-TR01-KA203-034929 provided by the Turkish National Agency. The research is also supported by the project LO 1506 of the Czech Ministry of Education, Youth and Sports. The authors appreciate the access to computing and storage facilities owned by parties and projects contributing to the National Grid Infrastructure MetaCentrum provided under the program “Projects of Large Research, Development, and Innovations Infrastructures” (CESNET LM2015042).
- 7.Grieg, D.M., Porteous, B.T., Scheult, A.H.: Exact maximum a posteriori estimation for binary images. J. R. Stat. Soc. 51(2), 271–279 (1989)Google Scholar
- 8.Jirik, M., Lukes, V.: imcut - 3D multiscale Graph-Cut segmentation module for python (2018). https://github.com/mjirik/imcut
- 9.Jirik, M., Lukeš, V.: LISA - Liver Surgery Analyser. https://github.com/mjirik/lisa
- 10.Kang, S.M., Wan, J.W.L.: A multiscale graph cut approach to bright-field multiple cell image segmentation using a Bhattacharyya measure. In: Proceedings of SPIE 8669, Medical Imaging 2013: Image Processing, p. 86693S (2013)Google Scholar