Uncertainty Estimation in Landmark Localization Based on Gaussian Heatmaps

Christian Payer, Martin Urschler, Horst Bischof, Darko Stern

Research output: Contribution to conferencePaperpeer-review

Abstract

In landmark localization, due to ambiguities in defining their exact position, landmark annotations may suffer from both large inter- and intra-observer variabilites, which result in uncertain annotations. Therefore, predicting a single coordinate for a landmark is not sufficient for modeling the distribution of possible landmark locations. We propose to learn the Gaussian covariances of target heatmaps, such that covariances for pointed heatmaps correspond to more certain landmarks and covariances for flat heatmaps to more uncertain or ambiguous landmarks. By fitting Gaussian functions to the predicted heatmaps, our method is able to obtain landmark location distributions, which model location uncertainties. We show on a dataset of left hand radiographs and on a dataset of lateral cephalograms that the predicted uncertainties correlate with the landmark error, as well as inter-observer variabilities.
Original languageEnglish
Pages42-51
Number of pages10
DOIs
Publication statusPublished - 8 Oct 2020
Event2nd International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging: UNSURE 2020 - Virtual, Lima, Peru
Duration: 8 Oct 2020 → …

Workshop

Workshop2nd International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging
CountryPeru
CityVirtual, Lima
Period8/10/20 → …

Keywords

  • Landmark localization
  • Uncertainty estimation

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this