PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation
This addresses the challenge of zero-shot generalization in medical imaging for clinicians and researchers, offering a novel approach that reduces reliance on labeled data while being incremental in its integration of synthetic supervision.
The paper tackled the problem of data scarcity in cardiac MRI segmentation by proposing a fully supervised few-shot learning framework that uses pathology-guided synthetic supervision, achieving a 4.2-11% Dice improvement over state-of-the-art methods with only 7 labeled anchors and approaching fully supervised performance with 19 anchors.
Few-shot learning (FSL) mitigates data scarcity in cardiac MRI segmentation but typically relies on semi-supervised techniques sensitive to domain shifts and validation bias, restricting zero-shot generalizability. We propose PathCo-LatticE, a fully supervised FSL framework that replaces unlabeled data with pathology-guided synthetic supervision. First, our Virtual Patient Engine models continuous latent disease trajectories from sparse clinical anchors, using generative modeling to synthesize physiologically plausible, fully labeled 3D cohorts. Second, Self-Reinforcing Interleaved Validation (SIV) provides a leakage-free protocol that evaluates models online with progressively challenging synthetic samples, eliminating the need for real validation data. Finally, a dynamic Lattice-of-Experts (LoE) organizes specialized networks within a pathology-aware topology and activates the most relevant experts per input, enabling robust zero-shot generalization to unseen data without target-domain fine-tuning. We evaluated PathCo-LatticE in a strict out-of-distribution (OOD) setting, deriving all anchors and severity statistics from a single-source domain (ACDC) and performing zero-shot testing on the multi-center, multi-vendor M&Ms dataset. PathCo-LatticE outperforms four state-of-the-art FSL methods by 4.2-11% Dice starting from only 7 labeled anchors, and approaches fully supervised performance (within 1% Dice) with only 19 labeled anchors. The method shows superior harmonization across four vendors and generalization to unseen pathologies. [Code will be made publicly available].