Combining patch-based strategies and non-rigid registration-based label fusion methods

TL;DR

This paper introduces a novel patch-based label fusion method that combines similarity measures and non-rigid registration to improve brain MRI segmentation accuracy and robustness, outperforming existing methods.

Contribution

The study presents a new patch-based label fusion approach integrating intensity and labeling similarities with non-rigid registration, enhancing segmentation performance.

Findings

Achieved mean Dice coefficients of 0.847 and 0.798 on two MRI datasets.

Method improves patch selection and weighting robustness.

Approach is efficient and competitive with recent methods.

Abstract

The objective of this study is to develop a patch-based labeling method that cooperates with a label fusion using non-rigid registrations. We present a novel patch-based label fusion method, whose selected patches and their weights are calculated from a combination of similarity measures between patches using intensity-based distances and labeling-based distances, where a previous labeling of the target image is inferred through a label fusion method using non-rigid registrations. These combined similarity measures result in better selection of the patches, and their weights are more robust, which improves the segmentation results compared to other label fusion methods, including the conventional patch-based labeling method. To evaluate the performance and the robustness of the proposed label fusion method, we employ two available databases of T1-weighted (T1W) magnetic resonance imaging (MRI) of human brains. We compare our approach with other label fusion methods in the automatic hippocampal segmentation from T1W-MRI. Our label fusion method yields mean Dice coefficients of 0.847 and 0.798 for the two databases used with mean times of approximately 180 and 320 seconds, respectively. The collaboration between the patch-based labeling method and the label fusion using non-rigid registrations is given in the several levels: (a) The pre-selection of the patches in the atlases are improved, (b) The weights of our selected patches are also more robust, (c) our approach imposes geometrical restrictions, such as shape priors, and (d) the work-flow is very efficient. We show that the proposed approach is very competitive with respect to recently reported methods.