Deep learning with uncertainty quantification in MRI-guided radiation therapy

150 150 MaLMIC - Machine Learning in Medical Imaging Consortium

Open Forum on Reproducibility and Good Practices in Machine Learning Research

Presenter:

Matt Hemsley

Abstract:

Deep learning methods are able to match or surpass the performance of ​​classical methods as well as human experts in a growing number of medical imaging related tasks. However, most deep learning methods are unable to quantify uncertainty, hindering clinical translation. In this talk, Matt presented an overview of techniques used to model uncertainty on network output, demonstrated the connection between uncertainty quantification and reproducibility, and presented examples where uncertainty estimates were obtained from networks that performed clinical tasks related to real-time MRI-guided adaptive radiation therapy.

Modality:

  • CT
  • MR

Organ:

  • Brain
  • Head and Neck

Disease

  • Cancer