When Weak Becomes Strong: Robust Quantification of White Matter Hyperintensities on Brain MRIs

In clinical practice, as a first approximation, the severity of an abnormality on an image is often determined by measuring its volume. Researchers often first segment this abnormality with a neural network trained by voxel-wise labels and thereafter extract the volume. Instead of this indirect two steps approach, we propose to train neural...

Balancing Costs and Benefits in Selecting New Information: Efficient Monitoring Using Deterministic Hydro-economic Models

Uncertainty reduces reliability and performance of water system operations. A decision-maker can take action, accepting the present uncertainty and facing its risks, or reduce uncertainty by first obtaining additional information. Information, however, comes at a cost. The decision-maker must therefore efficiently use his/her resources,...