DuMeta++: Spatiotemporal Dual Meta-Learning for Generalizable Few-Shot Brain Tissue Segmentation Across Diverse Ages
This addresses the problem of inconsistent brain tissue segmentation across the human lifespan for neuroscience and clinical applications, representing a novel method for a known bottleneck.
The paper tackles the challenge of generalizable brain tissue segmentation across ages without paired longitudinal data by proposing DuMeta++, a dual meta-learning framework, achieving improved cross-age generalization in few-shot settings on diverse datasets.
Accurate segmentation of brain tissues from MRI scans is critical for neuroscience and clinical applications, but achieving consistent performance across the human lifespan remains challenging due to dynamic, age-related changes in brain appearance and morphology. While prior work has sought to mitigate these shifts by using self-supervised regularization with paired longitudinal data, such data are often unavailable in practice. To address this, we propose \emph{DuMeta++}, a dual meta-learning framework that operates without paired longitudinal data. Our approach integrates: (1) meta-feature learning to extract age-agnostic semantic representations of spatiotemporally evolving brain structures, and (2) meta-initialization learning to enable data-efficient adaptation of the segmentation model. Furthermore, we propose a memory-bank-based class-aware regularization strategy to enforce longitudinal consistency without explicit longitudinal supervision. We theoretically prove the convergence of our DuMeta++, ensuring stability. Experiments on diverse datasets (iSeg-2019, IBIS, OASIS, ADNI) under few-shot settings demonstrate that DuMeta++ outperforms existing methods in cross-age generalization. Code will be available at https://github.com/ladderlab-xjtu/DuMeta++.