Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping

TL;DR

This paper introduces a plug-and-play shape refinement framework that improves brain skull stripping across diverse datasets with different imaging parameters and ages, leveraging invariant brain shape priors.

Contribution

The proposed framework addresses domain shift issues in skull stripping by using shape priors, avoiding retraining for each new domain and enhancing generalization across multi-site and lifespan datasets.

Findings

Outperforms state-of-the-art methods on multi-site lifespan datasets.

Effectively handles domain differences without retraining.

Utilizes invariant brain shape priors for robust segmentation.

Abstract

Skull stripping is a crucial prerequisite step in the analysis of brain magnetic resonance images (MRI). Although many excellent works or tools have been proposed, they suffer from low generalization capability. For instance, the model trained on a dataset with specific imaging parameters cannot be well applied to other datasets with different imaging parameters. Especially, for the lifespan datasets, the model trained on an adult dataset is not applicable to an infant dataset due to the large domain difference. To address this issue, numerous methods have been proposed, where domain adaptation based on feature alignment is the most common. Unfortunately, this method has some inherent shortcomings, which need to be retrained for each new domain and requires concurrent access to the input images of both domains. In this paper, we design a plug-and-play shape refinement (PSR) framework for multi-site and lifespan skull stripping. To deal with the domain shift between multi-site lifespan datasets, we take advantage of the brain shape prior, which is invariant to imaging parameters and ages. Experiments demonstrate that our framework can outperform the state-of-the-art methods on multi-site lifespan datasets.