🤖 AI Summary
This work addresses the cold-start challenge in 3D medical image segmentation, where initial annotations are absent, by proposing the CSCS framework—a novel active learning approach that incorporates geometric structure awareness of the dataset without requiring any labeled data. CSCS leverages both local representativeness in a self-supervised embedding space and reconstruction uncertainty to design a difficulty–coverage ratio statistic and a closed-form weight scheduling mechanism, enabling efficient sample selection without pretraining. Experiments across four diverse datasets—BraTS, FeTA, Spleen, and fetal MRI—demonstrate that CSCS significantly outperforms existing baselines under low-to-moderate annotation budgets, substantially enhancing the robustness and initialization efficiency of active learning in 3D medical image segmentation.
📝 Abstract
Deep learning for 3D medical image segmentation requires extensive manual annotations, a major bottleneck in volumetric medical imaging. Active learning aims to reduce this burden by selecting informative samples for annotation, but most methods assume that an initial labeled set is already available. This leaves the cold-start problem largely unresolved: how to select the first volumes from a fully unlabeled pool before any task-specific model is trained. We propose CSCS, a Curriculum-Stratified Cold-Start framework that adapts initial sample selection to the structure of the unlabeled dataset. CSCS combines two self-supervised, label-free signals: local typicality, measuring representativeness in the embedding space, and reconstruction-based uncertainty, used as a proxy for sample difficulty. These signals are combined through a weighted geometric score, where the weighting is determined by a closed-form pacing rule based on the effective annotation budget and the Difficulty-Coverage Ratio, a pool-level statistic measuring the alignment between difficulty and representativeness. We evaluate CSCS on four 3D medical image segmentation benchmarks: BraTS, FeTA, Spleen, and an in-house fetal MRI dataset. Using nnU-Net as downstream segmentation model, CSCS shows consistently competitive performance across datasets and annotation budgets, with the strongest gains in low-to-mid annotation regimes. These results suggest that dataset-aware cold-start initialization can improve the robustness of active learning for 3D medical image segmentation by adapting sample selection to the geometry of the unlabeled pool.