Publications
Filter by type:
Uncertainty Quantification in Medical Image Synthesis
Book Chapter in Biomedical Image Synthesis and Simulation: Methods and Applications, 2022.
Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels
In ICCV, Oral (top ~4%), * equal contributions, 2019.
Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning
In MICCAI, Spotlight (top ~5%), 2018.
Bayesian Image Quality Transfer
We propose a Bayesian variant of random forests, which provides an estimate of uncertainty over prediction which can be used to assess its accuracy in the absence of ground truth. We have shown that the predictive uncertainly correlates well with the accuracy and can highlight abnormality not represented in the training data.
In MICCAI, 2016.