Orientation Estimation of Abdominal Ultrasound Images with Multi-Hypotheses NetworksDownload PDF

10 Dec 2021, 14:21 (edited 22 Jun 2022)MIDL 2022Readers: Everyone
  • Keywords: ultrasound, abdominal, deep learning, orientation, multi-hypotheses, confidence, uncertainty
  • TL;DR: Multi-hypotheses networks are a simple and efficient alternative baseline to dropout and ensembling for uncertainty estimation.
  • Abstract: Ultrasound imaging can provide valuable information to clinicians during interventions, in particular when fused with other modalities. Multi-modal image registration algorithms however require a somewhat accurate initialization, which is particularly difficult to estimate for ultrasound images as their orientation is arbitrary and their content ambiguous (limited field of view, artifacts, etc.). In this work, we train neural networks to predict the absolute orientation of ultrasound frames, but also to produce a confidence for each prediction. This allows us to select only the most confident frames in the clip. Our networks are trained to produce multiple hypotheses using a simple yet overlooked meta-loss that is specifically designed to capture the ambiguity of the input data. We show on several abdominal ultrasound datasets that multi-hypotheses networks provide better uncertainty estimates than Monte-Carlo dropout while being more efficient than network ensembling. Generic, easy to implement and able to quantify both data ambiguity and out-of-distribution samples, they represent a preferable alternative to traditional baselines for uncertainty estimation. Our method produces on a clinical test estimates within $20^{\circ}$ of the true orientation, which we can use to improve the accuracy of a subsequent registration algorithm down to less than $10^{\circ}$.
  • Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
  • Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
  • Paper Type: validation/application paper
  • Primary Subject Area: Uncertainty Estimation
  • Secondary Subject Area: Application: Other
  • Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
  • Code And Data: We provided the code for setting up the multi-hypotheses network in Appendix A. The datasets used are private datasets from volunteers for which we only have consent for internal use.
6 Replies