• Publications
  • Influence
An Unsupervised Learning Model for Deformable Medical Image Registration
TLDR
The proposed method uses a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field, and demonstrates registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Expand
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
TLDR
VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster. Expand
Detecting Pulse from Head Motions in Video
TLDR
This method tracks features on the head and performs principal component analysis (PCA) to decompose their trajectories into a set of component motions and chooses the component that best corresponds to heartbeats based on its temporal frequency spectrum. Expand
Synthesizing Images of Humans in Unseen Poses
TLDR
A modular generative neural network is presented that synthesizes unseen poses using training pairs of images and poses taken from human action videos, separates a scene into different body part and background layers, moves body parts to new locations and refines their appearances, and composites the new foreground with a hole-filled background. Expand
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
TLDR
This paper presents a probabilistic generative model and derive an unsupervised learning-based inference algorithm that makes use of recent developments in convolutional neural networks (CNNs) and results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees and uncertainty estimates. Expand
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation
TLDR
This work learns a model of transformations from the images, and uses the model along with the labeled example to synthesize additional labeled examples, enabling the synthesis of complex effects such as variations in anatomy and image acquisition procedures. Expand
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
TLDR
A probabilistic generative model is presented and an unsupervised learning-based inference algorithm is derived that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). Expand
When and Why Test-Time Augmentation Works
TLDR
Analysis of theoretical and experimental analyses that shed light on when test time augmentation is likely to be helpful and when to use various test-time augmentation policies suggest that the nature and amount of training data, the model architecture, and the augmentation policy all matter. Expand
Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions
TLDR
The method can recover human gait videos and face images from spatial projections, and then show that it can recover videos of moving digits from dramatically motion-blurred images obtained via temporal projection. Expand
Scalable personalized medicine with active learning: detecting seizures with minimum labeled data
TLDR
The use of active learning is explored to allow for scalable personalized medicine based on physiological data and it is hypothesized that active learning can substantially reduce the amount of data that must be analyzed by experts while creating automated decision-support systems that are both personalized and highly accurate. Expand
...
1
2
3
...