Search papers, labs, and topics across Lattice.
This study introduces a Bayesian adaptively-weighted ensemble framework for few-shot abdominal segmentation, addressing the limitations of existing fixed-weight ensemble methods that fail to account for varying performance across anatomical targets and institutions. By leveraging a small labeled support set and employing Bayesian optimization, the framework dynamically adjusts model contributions to maximize segmentation accuracy on a target-domain validation set. The results show statistically significant improvements over traditional few-shot learners and state-of-the-art ensembling approaches, highlighting its effectiveness in clinical settings with limited annotations.
By adapting model contributions to specific anatomical targets and institutional contexts, this framework significantly enhances segmentation performance in environments with scarce labeled data.
Few-shot learning has emerged as a promising approach for anatomical segmentation when labelled data are scarce. However, different few-shot learning algorithms exhibit complementary strengths and weaknesses, with performance varying across anatomical targets and institutions. Existing few-shot segmentation ensembles, that combine predictions from multiple algorithms, typically employ fixed weighting schemes and therefore cannot adjust model contributions according to the target domain. In this work, we propose a Bayesian adaptively-weighted ensemble framework for segmentation under label scarcity and domain shift. Multiple few-shot segmentation algorithms are first adapted using a small labelled support set. Bayesian optimisation is then used to automatically identify ensemble weights that maximise segmentation performance on a target-domain validation set. The learned weights are subsequently fixed and applied to combine predictions on previously unseen query images from the target domain. The proposed framework is evaluated on the Cross-institution Male Pelvic Structures dataset using held-out anatomical structures and institutions to simulate simultaneous label scarcity and institutional domain shift. Results demonstrate statistically significant improvements over individual few-shot learners, fixed-weight ensembles, training-from-scratch baselines and recent state-of-the-art ensembling approaches. By adapting model contributions to the target anatomy and institutional domain, the proposed framework provides a practical mechanism for deploying segmentation systems to new clinical sites under severe annotation constraints.
