Finally Outshining the Random Baseline: A Simple and Effective Solution for Active Learning in 3D Biomedical Imaging

2026-01-20

AI Summary

This work addresses the limited performance gains of existing active learning methods over enhanced random sampling baselines in 3D biomedical image segmentation, primarily attributed to class imbalance and insufficient query diversity. To overcome these challenges, the authors propose ClaSP PE, a novel query strategy that integrates class-stratified sampling, logarithmic-scale power-law noise injection, and a decay scheduling mechanism to promote diversity during early acquisition rounds while focusing on high-value samples in later stages. Implemented within the nnActive framework without requiring task-specific hyperparameter tuning, ClaSP PE consistently outperforms random baselines across 24 experimental settings on four datasets, achieving simultaneous improvements in segmentation accuracy and annotation efficiency. Furthermore, the method demonstrates robust generalization on four unseen datasets, confirming its stability and broad applicability.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Representation, semantic annotation, enhancement, enrichments, access and/or integration of a variety of data on the Web

Abstract

Active learning (AL) has the potential to drastically reduce annotation costs in 3D biomedical image segmentation, where expert labeling of volumetric data is both time-consuming and expensive. Yet, existing AL methods are unable to consistently outperform improved random sampling baselines adapted to 3D data, leaving the field without a reliable solution. We introduce Class-stratified Scheduled Power Predictive Entropy (ClaSP PE), a simple and effective query strategy that addresses two key limitations of standard uncertainty-based AL methods: class imbalance and redundancy in early selections. ClaSP PE combines class-stratified querying to ensure coverage of underrepresented structures and log-scale power noising with a decaying schedule to enforce query diversity in early-stage AL and encourage exploitation later. In our evaluation on 24 experimental settings using four 3D biomedical datasets within the comprehensive nnActive benchmark, ClaSP PE is the only method that generally outperforms improved random baselines in terms of both segmentation quality with statistically significant gains, whilst remaining annotation efficient. Furthermore, we explicitly simulate the real-world application by testing our method on four previously unseen datasets without manual adaptation, where all experiment parameters are set according to predefined guidelines. The results confirm that ClaSP PE robustly generalizes to novel tasks without requiring dataset-specific tuning. Within the nnActive framework, we present compelling evidence that an AL method can consistently outperform random baselines adapted to 3D segmentation, in terms of both performance and annotation efficiency in a realistic, close-to-production scenario. Our open-source implementation and clear deployment guidelines make it readily applicable in practice. Code is at https://github.com/MIC-DKFZ/nnActive.

Problem

• active learning
• 3D biomedical imaging
• annotation efficiency
• random baseline
• image segmentation

Innovation

• active learning
• 3D biomedical imaging
• class imbalance
• query diversity
• predictive entropy