Competitive Ensembling Teacher-Student Framework for Semi-Supervised Left Atrium MRI Segmentation

TL;DR

This paper introduces a competitive ensembling teacher-student framework for semi-supervised left atrium MRI segmentation, leveraging mutual learning of student models and a competitive ensembling strategy to improve segmentation accuracy using unlabeled data.

Contribution

It proposes a novel collaborative learning framework with two student models and a competitive ensembling strategy, enhancing semi-supervised segmentation performance over existing methods.

Findings

Achieves superior segmentation accuracy on the LA dataset.

Effectively exploits unlabeled data for improved performance.

Outperforms several existing semi-supervised methods.

Abstract

Semi-supervised learning has greatly advanced medical image segmentation since it effectively alleviates the need of acquiring abundant annotations from experts and utilizes unlabeled data which is much easier to acquire. Among existing perturbed consistency learning methods, mean-teacher model serves as a standard baseline for semi-supervised medical image segmentation. In this paper, we present a simple yet efficient competitive ensembling teacher student framework for semi-supervised for left atrium segmentation from 3D MR images, in which two student models with different task-level disturbances are introduced to learn mutually, while a competitive ensembling strategy is performed to ensemble more reliable information to teacher model. Different from the one-way transfer between teacher and student models, our framework facilitates the collaborative learning procedure of different student models with the guidance of teacher model and motivates different training networks for a competitive learning and ensembling procedure to achieve better performance. We evaluate our proposed method on the public Left Atrium (LA) dataset and it obtains impressive performance gains by exploiting the unlabeled data effectively and outperforms several existing semi-supervised methods.