Iterative pseudo-labeling based adaptive copy-paste supervision for semi-supervised tumor segmentation

2025-08-05

AI Summary

Addressing the challenges of scarce annotated data for small and multiple lesions, and inadequate fine-grained lesion modeling in existing semi-supervised methods, this paper proposes an iterative pseudo-label-driven adaptive copy-paste supervision framework. Our approach comprises three key contributions: (1) a bidirectional uncertainty-guided adaptive augmentation mechanism that differentially strengthens labeled and unlabeled samples; (2) an iterative pseudo-label optimization strategy integrating mean-teacher consistency and consistency regularization to improve pseudo-label quality—particularly in complex tumor regions; and (3) an adaptive copy-paste data augmentation paradigm that enhances feature capture for small-volume and irregular lesions. Evaluated on multiple public and internal CT datasets, our method achieves significant performance gains over state-of-the-art approaches under only 10% labeling budget, demonstrating superior generalizability and robustness.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Semi-supervised learning (SSL) has attracted considerable attention in medical image processing. The latest SSL methods use a combination of consistency regularization and pseudo-labeling to achieve remarkable success. However, most existing SSL studies focus on segmenting large organs, neglecting the challenging scenarios where there are numerous tumors or tumors of small volume. Furthermore, the extensive capabilities of data augmentation strategies, particularly in the context of both labeled and unlabeled data, have yet to be thoroughly investigated. To tackle these challenges, we introduce a straightforward yet effective approach, termed iterative pseudo-labeling based adaptive copy-paste supervision (IPA-CP), for tumor segmentation in CT scans. IPA-CP incorporates a two-way uncertainty based adaptive augmentation mechanism, aiming to inject tumor uncertainties present in the mean teacher architecture into adaptive augmentation. Additionally, IPA-CP employs an iterative pseudo-label transition strategy to generate more robust and informative pseudo labels for the unlabeled samples. Extensive experiments on both in-house and public datasets show that our framework outperforms state-of-the-art SSL methods in medical image segmentation. Ablation study results demonstrate the effectiveness of our technical contributions.

Problem

• Segments numerous or small tumors in CT scans
• Enhances semi-supervised learning with adaptive augmentation
• Improves pseudo-label robustness for unlabeled data

Innovation

• Iterative pseudo-labeling for robust tumor segmentation
• Two-way uncertainty based adaptive augmentation mechanism
• Adaptive copy-paste supervision in semi-supervised learning