Search papers, labs, and topics across Lattice.
This paper introduces Multiple Prototype Contrastive Learning (MPCL), a novel framework for Semi-Supervised Medical Image Segmentation (SSMIS) that effectively leverages intra-class heterogeneity in medical images. By implementing three key innovations鈥擨ntensity-aligned Heterogeneous Prototype Generation (IHPG), Prototypical Space Optimization (PSO), and Dual-branch Knowledge Alignment (DKA)鈥攖he method enhances both diversity and precision in segmentation tasks. Extensive experiments reveal that MPCL significantly outperforms existing approaches, particularly in scenarios with limited labeled data, suggesting a new paradigm for medical image analysis.
Achieving precise medical image segmentation with limited labeled data is now possible by embracing intra-class heterogeneity through innovative prototype learning.
Due to the scarcity of expert-annotated data, Semi-Supervised Medical Image Segmentation (SSMIS) has emerged as a promising approach. Many anatomical structures in medical images exhibit significant intra-class heterogeneity, with different regions showing heterogeneous intensity patterns within the same structure. However, existing methods inadequately exploit this intensity-manifested intra-class heterogeneity, resulting in uniform structural representations and imprecise segmentation. Furthermore, the scarcity of labeled data makes it more difficult to effectively capture such complex heterogeneity. To address this, we propose Multiple Prototype Contrastive Learning (MPCL), an SSMIS framework that possesses better diversity and better precision. It consists of three novel designs: First, we provide structural representations with better diversity and propose Intensity-aligned Heterogeneous Prototype Generation (IHPG) that effectively models intra-class heterogeneity by generating multiple prototypes aligned with intensity characteristics. Second, we further enhance more diverse structural representations and build a solid foundation for more precise segmentation through Prototypical Space Optimization (PSO) that systematically optimizes a more discriminative and generalizable prototypical space. Finally, we achieve segmentation results with better precision through Dual-branch Knowledge Alignment (DKA) that efficiently promotes intra-class heterogeneity knowledge transfer from prototypical space to the segmentation network. Extensive experiments on three medical image datasets with significant intra-class heterogeneity demonstrate that MPCL significantly outperforms existing methods, especially under extremely limited labeled data. We believe this multiple prototype learning framework offers a novel paradigm for leveraging intra-class heterogeneity in medical images, which will provide an effective benchmark for SSMIS and advance the field of medical image analysis. Our code is publicly available at https://github.com/rhodaliu17/MPCL.
