Coordinative Learning with Ordinal and Relational Priors for Volumetric Medical Image Segmentation
This work addresses segmentation challenges in medical imaging for applications like diagnosis and treatment planning, representing an incremental improvement over prior contrastive methods.
The paper tackles the problem of volumetric medical image segmentation under limited annotations by addressing how existing methods discard continuous anatomical similarity information and ignore global directional consistency, resulting in distorted feature spaces. The proposed CORAL method achieves state-of-the-art performance on benchmark datasets in limited-annotation settings.
Volumetric medical image segmentation presents unique challenges due to the inherent anatomical structure and limited availability of annotations. While recent methods have shown promise by contrasting spatial relationships between slices, they rely on hard binary thresholds to define positive and negative samples, thereby discarding valuable continuous information about anatomical similarity. Moreover, these methods overlook the global directional consistency of anatomical progression, resulting in distorted feature spaces that fail to capture the canonical anatomical manifold shared across patients. To address these limitations, we propose Coordinative Ordinal-Relational Anatomical Learning (CORAL) to capture both local and global structure in volumetric images. First, CORAL employs a contrastive ranking objective to leverage continuous anatomical similarity, ensuring relational feature distances between slices are proportional to their anatomical position differences. In addition, CORAL incorporates an ordinal objective to enforce global directional consistency, aligning the learned feature distribution with the canonical anatomical progression across patients. Learning these inter-slice relationships produces anatomically informed representations that benefit the downstream segmentation task. Through this coordinative learning framework, CORAL achieves state-of-the-art performance on benchmark datasets under limited-annotation settings while learning representations with meaningful anatomical structure. Code is available at https://github.com/haoyiwang25/CORAL.