A Unified Framework for Semi-Supervised Image Segmentation and Registration

2025-02-05

AI Summary

To address the scarcity and high acquisition cost of high-quality annotations in medical image segmentation, this paper proposes a joint segmentation–registration semi-supervised learning framework. The method innovatively integrates deformable image registration into the semi-supervised segmentation pipeline: the registration model generates geometrically consistent pseudo-labels for unlabeled images, which are refined via consistency regularization and end-to-end co-optimization. Evaluated on a 2D brain dataset using only 1% labeled data, our approach significantly outperforms mainstream teacher–student paradigms, achieving substantial improvements in Dice score while demonstrating strong generalizability and robustness. The core contribution lies in leveraging geometric constraints—enforced through registration—to guide pseudo-label generation, thereby enabling joint modeling and joint optimization of segmentation and registration tasks.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• 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
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Semi-supervised learning, which leverages both annotated and unannotated data, is an efficient approach for medical image segmentation, where obtaining annotations for the whole dataset is time-consuming and costly. Traditional semi-supervised methods primarily focus on extracting features and learning data distributions from unannotated data to enhance model training. In this paper, we introduce a novel approach incorporating an image registration model to generate pseudo-labels for the unannotated data, producing more geometrically correct pseudo-labels to improve the model training. Our method was evaluated on a 2D brain data set, showing excellent performance even using only 1% of the annotated data. The results show that our approach outperforms conventional semi-supervised segmentation methods (e.g. teacher-student model), particularly in a low percentage of annotation scenario. GitHub: https://github.com/ruizhe-l/UniSegReg.

Problem

• Semi-supervised learning for medical image segmentation
• Image registration to generate accurate pseudo-labels
• Improved performance with minimal annotated data

Innovation

• Semi-supervised learning integration
• Image registration for pseudo-labels
• Enhanced geometric accuracy training