Decoupled Competitive Framework for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces a Decoupled Competitive Framework (DCF) for semi-supervised medical image segmentation that addresses limitations of existing methods by decoupling student-teacher interactions and enabling effective knowledge exchange, leading to improved performance.

Contribution

The paper proposes a novel decoupled competitive framework that mitigates over-coupling and cognitive bias in semi-supervised segmentation models, enhancing their efficacy.

Findings

Outperforms previous state-of-the-art methods on three datasets

Effective decoupling improves model stability and accuracy

Framework applicable to both 2D and 3D medical images

Abstract

Confronting the critical challenge of insufficiently annotated samples in medical domain, semi-supervised medical image segmentation (SSMIS) emerges as a promising solution. Specifically, most methodologies following the Mean Teacher (MT) or Dual Students (DS) architecture have achieved commendable results. However, to date, these approaches face a performance bottleneck due to two inherent limitations, \textit{e.g.}, the over-coupling problem within MT structure owing to the employment of exponential moving average (EMA) mechanism, as well as the severe cognitive bias between two students of DS structure, both of which potentially lead to reduced efficacy, or even model collapse eventually. To mitigate these issues, a Decoupled Competitive Framework (DCF) is elaborated in this work, which utilizes a straightforward competition mechanism for the update of EMA, effectively decoupling students and teachers in a dynamical manner. In addition, the seamless exchange of invaluable and precise insights is facilitated among students, guaranteeing a better learning paradigm. The DCF introduced undergoes rigorous validation on three publicly accessible datasets, which encompass both 2D and 3D datasets. The results demonstrate the superiority of our method over previous cutting-edge competitors. Code will be available at https://github.com/JiaheChen2002/DCF.