MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification

2025-09-30

AI Summary

Existing few-shot whole-slide image (WSI) classification methods predominantly rely on slide-level prompts, failing to capture subtype-specific phenotypic variations of histological entities—such as nuclei and glands—thus limiting fine-grained pathological diagnosis. To address this, we propose MAPLE, a Multi-scale Attribute-enhanced Prompt Learning framework. MAPLE introduces entity-level prompt learning for the first time, integrating multi-scale histological entities with their phenotypic attributes. It incorporates an entity-guided cross-attention mechanism and a cross-scale entity graph learning module to enable fine-grained feature alignment and global semantic aggregation. Furthermore, large language models are leveraged to generate synergistic entity-level and slide-level prompts. Evaluated on three cancer cohorts, MAPLE achieves significant improvements in few-shot classification performance—enhancing subtype recognition accuracy while preserving strong global discriminative capability.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Prompt learning has emerged as a promising paradigm for adapting pre-trained vision-language models (VLMs) to few-shot whole slide image (WSI) classification by aligning visual features with textual representations, thereby reducing annotation cost and enhancing model generalization. Nevertheless, existing methods typically rely on slide-level prompts and fail to capture the subtype-specific phenotypic variations of histological entities (emph{e.g.,} nuclei, glands) that are critical for cancer diagnosis. To address this gap, we propose Multi-scale Attribute-enhanced Prompt Learning ( extbf{MAPLE}), a hierarchical framework for few-shot WSI classification that jointly integrates multi-scale visual semantics and performs prediction at both the entity and slide levels. Specifically, we first leverage large language models (LLMs) to generate entity-level prompts that can help identify multi-scale histological entities and their phenotypic attributes, as well as slide-level prompts to capture global visual descriptions. Then, an entity-guided cross-attention module is proposed to generate entity-level features, followed by aligning with their corresponding subtype-specific attributes for fine-grained entity-level prediction. To enrich entity representations, we further develop a cross-scale entity graph learning module that can update these representations by capturing their semantic correlations within and across scales. The refined representations are then aggregated into a slide-level representation and aligned with the corresponding prompts for slide-level prediction. Finally, we combine both entity-level and slide-level outputs to produce the final prediction results. Results on three cancer cohorts confirm the effectiveness of our approach in addressing few-shot pathology diagnosis tasks.

Problem

• Captures histological subtype variations for cancer diagnosis
• Integrates multi-scale visual semantics with entity-level predictions
• Addresses few-shot whole slide image classification challenges

Innovation

• Generates entity-level prompts using large language models
• Employs cross-scale entity graph learning for representation enrichment
• Combines multi-scale predictions for final slide classification