Purpose: To propose an robust fat water separation method using binary decision tree algorithm.
Methods: In this paper, a novel fat-water separation algorithm using binary decision tree is proposed. Pixels are firstly clustered into sub-regions. Different from existing region growing algorithms, the proposed method solves the phasor ambiguity problem region by region. The method was tested on data sets from ISMRM 2012 Challenge.
Results:Fat-water separation were successfully achieved by the proposed method in the datasets.
Conclusion: A novel method using binary decision tree algorithm is proposed for robust and accurate water-fat separation.