deep learning

Deep segmentation networks typically create their outputs via a softmax. Hence, the assignment appears to be probabilistic. However, it has been shown in literatute that interpreting these softmax outputs as label probabilities is not reliable and that they tend to be overly confident.

VoteNet is a deep-learning-based label fusion strategy for multi-atlas segmentation (MAS) which locally selects a set of reliable atlases whose labels are then fused via plurality voting. By selecting a good initial atlas set MAS with VoteNet significantly outperforms a number of other label fusion strategies as well as a direct deep-learning (DL) segmentation approach.

Analysis approaches for histology images; in particular, for appearance normalization.

Deformable image registration approaches via numerical optimization and deep learning.

We have developed multiple image segmentation methods.

Image analysis approaches for the quantitative analysis of osteoarthritis in the knee.

Topological analysis approaches, with a recent focus on integrating deep learning with topology.

Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE). Although important steps have been taken to realize the advantages of such …

Deep learning models have been successful in computer vision and medical image analysis. However, training these models frequently requires large labeled image sets whose creation is often very time and labor intensive, for example, in the context of …

Clustering and prediction are two primary tasks in the fields of unsupervised and supervised learning, respectively. Although much of the recent advances in machine learning have been centered around those two tasks, the interdependent, mutually …