Dual Teacher-Student Learning for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces dual teacher-student learning (DTSL), a semi-supervised approach for medical image segmentation that uses dual signals to regulate learning, outperforming existing methods and sometimes surpassing fully supervised models.

Contribution

The paper proposes DTSL, a novel semi-supervised learning framework that employs dual signals and a consensus label generator to improve segmentation accuracy.

Findings

DTSL outperforms state-of-the-art semi-supervised methods on four benchmarks.

On three datasets, semi-supervised DTSL surpasses fully supervised models.

The consensus label generator effectively guides learning with limited labeled data.

Abstract

Semi-supervised learning reduces the costly manual annotation burden in medical image segmentation. A popular approach is the mean teacher (MT) strategy, which applies consistency regularization using a temporally averaged teacher model. In this work, the MT strategy is reinterpreted as a form of self-paced learning in the context of supervised learning, where agreement between the teacher's predictions and the ground truth implicitly guides the model from easy to hard. Extending this insight to semi-supervised learning, we propose dual teacher-student learning (DTSL). It regulates the learning pace on unlabeled data using two signals: a temporally averaged signal from an in-group teacher and a cross-architectural signal from a student in a second, distinct model group. Specifically, a novel consensus label generator (CLG) creates the pseudo-labels from the agreement between these two signals, establishing an effective learning curriculum. Extensive experiments on four benchmark datasets demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches. Remarkably, on three of the four datasets, our semi-supervised method with limited labeled data surpasses its fully supervised counterparts, validating the effectiveness of our self-paced learning design.