OpenPath: Open-Set Active Learning for Pathology Image Classification via Pre-trained Vision-Language Models

2025-06-18

AI Summary

To address the low annotation efficiency of active learning (AL) in pathological image classification under open-set scenarios—where out-of-distribution (OOD) samples severely degrade model training—this paper proposes the first open-set AL framework for digital pathology. Methodologically, it innovatively integrates a task-oriented multi-class prompt-based coarse screening mechanism with the DIS sampling strategy: pre-trained vision-language models (VLMs) coupled with class-specific prompts enable efficient in-distribution (ID)/OOD separation; prototype-guided ID screening (PIS) and entropy-guided stochastic sampling (EGSS) jointly optimize sample purity and informativeness. Evaluated on two large-scale public pathological datasets, our framework significantly accelerates model convergence and improves final classification accuracy. It achieves state-of-the-art ID sample purity—outperforming existing open-set AL approaches—while maintaining high labeling efficiency and robustness to OOD interference.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Pathology image classification plays a crucial role in accurate medical diagnosis and treatment planning. Training high-performance models for this task typically requires large-scale annotated datasets, which are both expensive and time-consuming to acquire. Active Learning (AL) offers a solution by iteratively selecting the most informative samples for annotation, thereby reducing the labeling effort. However, most AL methods are designed under the assumption of a closed-set scenario, where all the unannotated images belong to target classes. In real-world clinical environments, the unlabeled pool often contains a substantial amount of Out-Of-Distribution (OOD) data, leading to low efficiency of annotation in traditional AL methods. Furthermore, most existing AL methods start with random selection in the first query round, leading to a significant waste of labeling costs in open-set scenarios. To address these challenges, we propose OpenPath, a novel open-set active learning approach for pathological image classification leveraging a pre-trained Vision-Language Model (VLM). In the first query, we propose task-specific prompts that combine target and relevant non-target class prompts to effectively select In-Distribution (ID) and informative samples from the unlabeled pool. In subsequent queries, Diverse Informative ID Sampling (DIS) that includes Prototype-based ID candidate Selection (PIS) and Entropy-Guided Stochastic Sampling (EGSS) is proposed to ensure both purity and informativeness in a query, avoiding the selection of OOD samples. Experiments on two public pathology image datasets show that OpenPath significantly enhances the model's performance due to its high purity of selected samples, and outperforms several state-of-the-art open-set AL methods. The code is available at href{https://github.com/HiLab-git/OpenPath}{https://github.com/HiLab-git/OpenPath}..

Problem

• Reduces labeling effort in pathology image classification via active learning
• Addresses inefficiency of traditional AL methods with OOD data
• Improves sample selection purity and informativeness using VLMs

Innovation

• Uses pre-trained Vision-Language Model (VLM)
• Task-specific prompts for initial query
• Diverse Informative ID Sampling (DIS)