Xu, Moucheng;
Zhou, Yukun;
Jin, Chen;
de Groot, Marius;
Alexander, Daniel C;
Oxtoby, Neil P;
Hu, Yipeng;
(2024)
Expectation maximisation pseudo labels.
Medical Image Analysis
, 94
, Article 103125. 10.1016/j.media.2024.103125.
Preview |
Text
1-s2.0-S1361841524000501-main.pdf - Published Version Download (3MB) | Preview |
Abstract
In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes’ theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high-quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi-class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo-labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.
Loading...
Loading...Loading...| 1. |  United States | 11 |
| 2. |  United Kingdom | 4 |
| 3. |  China | 3 |
| 4. |  India | 2 |
| 5. |  Germany | 2 |
| 6. |  Ireland | 1 |
| 7. |  Russian Federation | 1 |
| 8. |  Austria | 1 |
| 9. |  Spain | 1 |
| 10. |  Australia | 1 |
Archive Staff Only
 |
View Item |
