Multimodal Prototype Alignment for Semi-supervised Pathology Image Segmentation
This work addresses segmentation challenges in pathology images for medical diagnosis, offering a novel approach with text prototype supervision, though it is domain-specific and incremental in combining existing techniques.
The paper tackles the problem of ambiguous semantic boundaries and high annotation costs in pathological image segmentation by proposing MPAMatch, a semi-supervised framework that uses multimodal prototype alignment for pixel-level contrastive learning, achieving superior performance over state-of-the-art methods on datasets like GLAS and EBHI-SEG-GLAND.
Pathological image segmentation faces numerous challenges, particularly due to ambiguous semantic boundaries and the high cost of pixel-level annotations. Although recent semi-supervised methods based on consistency regularization (e.g., UniMatch) have made notable progress, they mainly rely on perturbation-based consistency within the image modality, making it difficult to capture high-level semantic priors, especially in structurally complex pathology images. To address these limitations, we propose MPAMatch - a novel segmentation framework that performs pixel-level contrastive learning under a multimodal prototype-guided supervision paradigm. The core innovation of MPAMatch lies in the dual contrastive learning scheme between image prototypes and pixel labels, and between text prototypes and pixel labels, providing supervision at both structural and semantic levels. This coarse-to-fine supervisory strategy not only enhances the discriminative capability on unlabeled samples but also introduces the text prototype supervision into segmentation for the first time, significantly improving semantic boundary modeling. In addition, we reconstruct the classic segmentation architecture (TransUNet) by replacing its ViT backbone with a pathology-pretrained foundation model (Uni), enabling more effective extraction of pathology-relevant features. Extensive experiments on GLAS, EBHI-SEG-GLAND, EBHI-SEG-CANCER, and KPI show MPAMatch's superiority over state-of-the-art methods, validating its dual advantages in structural and semantic modeling.