Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation
This work addresses efficient and robust segmentation for medical imaging, offering an incremental improvement by simplifying and generalizing pseudo-labeling methods.
The paper tackles semi-supervised segmentation by reformulating pseudo-labeling as an Expectation-Maximization algorithm, resulting in SegPL, which achieves competitive performance against state-of-the-art methods on medical image tasks with less computational cost and robustness to noise.
This paper concerns pseudo labelling in segmentation. Our contribution is fourfold. Firstly, we present a new formulation of pseudo-labelling as an Expectation-Maximization (EM) algorithm for clear statistical interpretation. Secondly, we propose a semi-supervised medical image segmentation method purely based on the original pseudo labelling, namely SegPL. We demonstrate SegPL is a competitive approach against state-of-the-art consistency regularisation based methods on semi-supervised segmentation on a 2D multi-class MRI brain tumour segmentation task and a 3D binary CT lung vessel segmentation task. The simplicity of SegPL allows less computational cost comparing to prior methods. Thirdly, we demonstrate that the effectiveness of SegPL may originate from its robustness against out-of-distribution noises and adversarial attacks. Lastly, under the EM framework, we introduce a probabilistic generalisation of SegPL via variational inference, which learns a dynamic threshold for pseudo labelling during the training. We show that SegPL with variational inference can perform uncertainty estimation on par with the gold-standard method Deep Ensemble.