Deep semi-supervised segmentation with weight-averaged consistency targets
This work addresses segmentation challenges in medical imaging with limited labeled data, but it is incremental as it expands an existing method to a new task.
The authors tackled semi-supervised segmentation by adapting the Mean Teacher approach to MRI data, achieving important improvements in a small data regime using a multi-center dataset.
Recently proposed techniques for semi-supervised learning such as Temporal Ensembling and Mean Teacher have achieved state-of-the-art results in many important classification benchmarks. In this work, we expand the Mean Teacher approach to segmentation tasks and show that it can bring important improvements in a realistic small data regime using a publicly available multi-center dataset from the Magnetic Resonance Imaging (MRI) domain. We also devise a method to solve the problems that arise when using traditional data augmentation strategies for segmentation tasks on our new training scheme.