English

More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation

Image and Video Processing 2019-08-23 v1 Computer Vision and Pattern Recognition Machine Learning Machine Learning

Abstract

Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications. With a laparoscopic liver image segmentation application, we investigate the performance impact by altering the quantities of labelled and unlabelled training data, using a semi-supervised segmentation algorithm based on the mean teacher learning paradigm. We first report a significantly higher segmentation accuracy, compared with supervised learning. Interestingly, this comparison reveals that the training strategy adopted in the semi-supervised algorithm is also responsible for this observed improvement, in addition to the added unlabelled data. We then compare different combinations of labelled and unlabelled data set sizes for training semi-supervised segmentation networks, to provide a quantitative example of the practically useful trade-off between the two data planning strategies in this surgical guidance application.

Keywords

Cite

@article{arxiv.1908.08035,
  title  = {More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation},
  author = {Yunguan Fu and Maria R. Robu and Bongjin Koo and Crispin Schneider and Stijn van Laarhoven and Danail Stoyanov and Brian Davidson and Matthew J. Clarkson and Yipeng Hu},
  journal= {arXiv preprint arXiv:1908.08035},
  year   = {2019}
}

Comments

Accepted to MICCAI MIL3ID 2019

R2 v1 2026-06-23T10:53:33.290Z