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

MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification, NeurIPS 2025. [arxiv]
Junjie Zhou, Wei Shao, Yagao Yue, Wei Mu, Peng Wan, Qi Zhu, Daoqiang Zhang

Summary: Here is the official implementation of the paper "MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification".

Table of Contents

• Introduction
• Requirements
• Data preparation
• Usage
• Acknowledgement

Introduction

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 (e.g., nuclei, glands) that are critical for cancer diagnosis. To address this gap, we propose Multi-scale Attribute-enhanced Prompt Learning (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.

Requirements

1. Create conda environment.

conda create -n maple python=3.9
conda activate maple

2. Install the required packages.

pip install -r requirements.txt

3. Check the installed packages.

conda list

Data preparation

WSIs

1. Downloading the original WSI data from TCGA
2. Preprocessing WSI data by CLAM.

The final structure of datasets should be as following:

DATA_ROOT_DIR/
    └──pt_files/
        ├── slide_1.pt
        ├── slide_2.pt
        └── ...

Usage

Please see run.sh

Acknowledgement

We would like to thank the following repositories for their great works:

• CLAM
• CoOp
• TOP
• MSCPT