A Unified Framework for Semi-Supervised Image Segmentation and Registration

TL;DR

This paper presents a unified semi-supervised image segmentation and registration framework that uses image registration to generate geometrically accurate pseudo-labels, significantly improving performance with minimal annotations.

Contribution

It introduces a novel registration-based pseudo-label generation method for semi-supervised segmentation, enhancing accuracy especially with limited annotated data.

Findings

Outperforms traditional semi-supervised methods like teacher-student models.

Achieves excellent results with only 1% annotated data.

Demonstrates robustness in low-annotation scenarios.

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.