Search Results for author:
Found 37 papers, 20 papers with code
Tyche: Stochastic In-Context Learning for Medical Image Segmentation
Existing learning-based solutions to medical image segmentation have two important shortcomings.
ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image
These include a training strategy that incorporates both a highly diverse set of images and tasks, novel algorithms for simulated user interactions and labels, and a network that enables fast inference.
GIST: Generating Image-Specific Text for Fine-grained Object Classification
We demonstrate the utility of GIST by fine-tuning vision-language models on the image-and-generated-text pairs to learn an aligned vision-language representation space for improved classification.
Fine-Grained Image Classification
Image-text Classification
+4
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series
However, most existing SSL methods for clinical time series are limited in that they are designed for unimodal time series, such as a sequence of structured features (e. g., lab values and vitals signs) or an individual high-dimensional physiological signal (e. g., an electrocardiogram).
Multi-Similarity Contrastive Learning
Given a similarity metric, contrastive methods learn a representation in which examples that are similar are pushed together and examples that are dissimilar are pulled apart.
Coarse race data conceals disparities in clinical risk score performance
Across outcomes and metrics, we show that the risk scores exhibit significant granular performance disparities within coarse race groups.
Magnitude Invariant Parametrizations Improve Hypernetwork Learning
In this work, we identify a fundamental and previously unidentified problem that contributes to the challenge of training hypernetworks: a magnitude proportionality between the inputs and outputs of the hypernetwork.
UniverSeg: Universal Medical Image Segmentation
We present UniverSeg, a method for solving unseen medical segmentation tasks without additional training.
Scale-Space Hypernetworks for Efficient Biomedical Imaging
We find that SSHN consistently provides a better accuracy-efficiency trade-off at a fraction of the training cost.
SizeGAN: Improving Size Representation in Clothing Catalogs
Online clothing catalogs lack diversity in body shape and garment size.
Improved Text Classification via Test-Time Augmentation
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models.
Data Augmentation for Electrocardiograms
In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks.
Learning the Effect of Registration Hyperparameters with HyperMorph
We design a meta network, or hypernetwork, that predicts the parameters of a registration network for input hyperparameters, thereby comprising a single model that generates the optimal deformation field corresponding to given hyperparameter values.
Multiplying Matrices Without Multiplying
Multiplying matrices is among the most fundamental and compute-intensive operations in machine learning.
Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction
Inference of latent variables in this model corresponds to both making a prediction and providing supporting evidence for that prediction.
HyperMorph: Amortized Hyperparameter Learning for Image Registration
We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training.
Exploiting structured data for learning contagious diseases under incomplete testing
In this work we ask: can we build reliable infection prediction models when the observed data is collected under limited, and biased testing that prioritizes testing symptomatic individuals?
Better Aggregation in Test-Time Augmentation
In this paper, we present 1) experimental analyses that shed light on cases in which the simple average is suboptimal and 2) a method to address these shortcomings.
Unsupervised Domain Adaptation in the Absence of Source Data
Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available.
Anatomical Predictions using Subject-Specific Medical Data
We present a method that predicts how a brain MRI for an individual will change over time.
What is the State of Neural Network Pruning?
Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years.
Image segmentation of liver stage malaria infection with spatial uncertainty sampling
Global eradication of malaria depends on the development of drugs effective against the silent, yet obligate liver stage of the disease.
Cultural Vocal Bursts Intensity Prediction
Image Segmentation
+2
Estimation of Bounds on Potential Outcomes For Decision Making
Estimation of individual treatment effects is commonly used as the basis for contextual decision making in fields such as healthcare, education, and economics.
Learning Conditional Deformable Templates with Convolutional Networks
We develop a learning framework for building deformable templates, which play a fundamental role in many image analysis and computational anatomy tasks.
Unsupervised Data Imputation via Variational Inference of Deep Subspaces
In this work, we introduce a general probabilistic model that describes sparse high dimensional imaging data as being generated by a deep non-linear embedding.
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs).
Ranked #2 on
Diffeomorphic Medical Image Registration
on OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP
Constrained Diffeomorphic Image Registration
Deformable Medical Image Registration
+2
Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
The integration of anatomical priors can facilitate CNN-based anatomical segmentation in a range of novel clinical problems, where few or no annotations are available and thus standard networks are not trainable.
Fast Learning-based Registration of Sparse 3D Clinical Images
We present a learning-based registration method, SparseVM, that is more accurate and orders of magnitude faster than the most accurate clinical registration methods.
Multiple Instance Learning for ECG Risk Stratification
We focus on estimating a patient's risk of cardiovascular death after an acute coronary syndrome based on a patient's raw electrocardiogram (ECG) signal.
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images.
Ranked #1 on
Diffeomorphic Medical Image Registration
on OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP
(Dice metric)
Deformable Medical Image Registration
Diffeomorphic Medical Image Registration
+1
Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
In this work, we present a two-step framework to 1) learn relevant patient subgroups, and 2) predict an outcome for separate patient populations in a multi-task framework, where each population is a separate task.
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
We demonstrate our method on a 3D brain registration task, and provide an empirical analysis of the algorithm.
Synthesizing Images of Humans in Unseen Poses
Given an image of a person and a desired pose, we produce a depiction of that person in that pose, retaining the appearance of both the person and background.
An Unsupervised Learning Model for Deformable Medical Image Registration
We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest.
Jiffy: A Convolutional Approach to Learning Time Series Similarity
Computing distances between examples is at the core of many learning algorithms for time series.
A Video-Based Method for Objectively Rating Ataxia
The performance of our system is comparable to that of a group of ataxia specialists in terms of mean error and correlation, and our system's predictions were consistently within the range of inter-rater variability.
Detecting Pulse from Head Motions in Video
We extract heart rate and beat lengths from videos by measuring subtle head motion caused by the Newtonian reaction to the influx of blood at each beat.
