Metric learning for label fusion in multi-atlas based image segmentation
Hancan Zhu, Hewei Cheng, Xuesong Yang, Yong Fan · 2016
A novel metric learning method is proposed to fuse segmentation labels in multi-atlas based image segmentation. Different from current label fusion methods that typically adopt a predefined distance metric model to compute the similarity between image patches of atlas images and the image to be segmented, we learn a distance metric model from the atlases to keep image patches of the same structure close to each other while those of different structures are separated. The learned distance metric model is then used to compute the similarity measure between image patches in the label fusion. The proposed method has been validated for segmenting hippocampus based on the EADC-ADNI dataset and the experimental results have demonstrated that our method can achieve better segmentation performance than the existing weighted voting label fusion methods with predefined metric models.