Uncertainty Estimates as Data Selection Criteria to Boost Omni-Supervised Learning

Lorenzo Venturini, Aris T. Papageorghiou, J. Alison Noble, Ana I. L. Namburete

Abstract

For many medical applications, large quantities of imaging data are routinely obtained but it can be difficult and time-consuming to obtain high-quality labels for that data. We propose a novel uncertainty-based method to improve the performance of segmentation networks when limited manual labels are available in a large dataset. We estimate segmentation uncertainty on unlabeled data using test-time augmentation and test-time dropout. We then use uncertainty metrics to select unlabeled samples for further training in a semi-supervised learning framework. Compared to random data selection, our method gives a significant boost in Dice coefficient for semi-supervised volume segmentation on the EADC-ADNI/HARP MRI dataset and the large-scale INTERGROWTH-21st ultrasound dataset. Our results show a greater performance boost on the ultrasound dataset, suggesting that our method is most useful with data of lower or more variable quality.
BibTeX
@inproceedings{venturini2020uncertainty,
  author = {Lorenzo Venturini and Aris T. Papageorghiou and J. Alison Noble and Ana I. L. Namburete},
  title = {{Uncertainty Estimates as Data Selection Criteria to Boost Omni-Supervised Learning}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2020},
  doi = {10.1007/978-3-030-59710-8\_67},
}

Loading related content...

Figure