Unified framework for medical image segmentation using active and semi-supervised learning.
problem Training medical image segmentation models with limited annotated data.
method RegAL, a unified active semi-supervised framework that optimizes sample acquisition and unlabeled data utilization.
result RegAL consistently outperforms state-of-the-art methods across various datasets and metrics under extreme annotation scarcity.
Deep learning methods quantify uncertainty in neuroimage enhancement.
problem Uncertainty in deep learning models for medical image enhancement.
method Heteroscedastic noise model and approximate Bayesian inference for uncertainty quantification.
result Uncertainty quantification improves predictive performance and risk assessment.
Proposes a multi-resolution model for prostate cancer classification using mpMRI.
problem Improving voxel-wise classification of prostate cancer using multi-parametric MRI data.
method Multi-resolution Super Learner framework combining local base learners at multiple resolutions and spatial Gaussian kernel smoothing.
result Enhanced voxel-wise classification of prostate cancer status and clinical significance.
fcHMRF-LIS controls FDR in neuroimaging data, improving power and scalability.
problem Complex spatial dependencies and high variability in FDR control methods for neuroimaging data.
method fcHMRF-LIS integrates LIS-based testing with fcHMRF to model spatial structures efficiently.
result fcHMRF-LIS achieves accurate FDR control, lower FNR, and higher true positives compared to existing methods.
3D CNNs interpret brain MRI differences between men and women.
problem Interpreting 3D CNNs for voxel-wise brain MRI analysis.
method Three interpretation methods: Meaningful Perturbations, Grad CAM, and Guided Backpropagation.
result Voxel-wise 3D CNN interpretation of brain MRI data.
MRI method predicts glioma features, survival, and endothelial proliferation.
problem Invasive biopsy limits detection of glioma features due to tumor heterogeneity.
method Voxel-wise, multiparametric MRI radiomics with k-NN classifier.
result Model accurately predicts disease compositions, survival, and endothelial proliferation.
Permutation testing is a non-parametric method for obtaining the max null distribution used to compute corrected p-values that provide strong control of false positives. In neuroimaging, however, the computational burden of running such an algorithm can be significant. We find that by viewing the permutation testing …
Diffusion MRI is the modality of choice to study alterations of white matter. In past years, various works have used diffusion MRI for automatic classification of AD. However, classification performance obtained with different approaches is difficult to compare and these studies are also difficult to reproduce. In the …
Proposes a strategy to train models with minimal labeled data.
problem Scarce and expensive labeled data for medical tasks.
method Recursive training strategy to use image-level annotations for pixel-level segmentation.
result Improved segmentation of intracranial hemorrhage in CT scans.
New biomarker predicts MRgFUS treatment outcome without contrast agents.
problem Inaccurate assessment of treated tissue viability after MRgFUS.
method Deep learning on noncontrast multiparametric MRI images, voxel-wise registration.
result Predicted follow-up NPV with DICE coefficient 0.71, outperforming current standard.
Adaptive sampling improves deep learning efficiency by focusing on informative samples.
problem Expensive annotations and loss of sample informativeness in deep learning.
method Adaptive latent space sampling based on hardness-aware strategy.
result The proposed framework outperforms random sampling on various datasets.
Event-based models (EBM) are a class of disease progression models that can be used to estimate temporal ordering of neuropathological changes from cross-sectional data. Current EBMs only handle scalar biomarkers, such as regional volumes, as inputs. However, regional aggregates are a crude summary of the underlying hi…
Non-invasive detection of cardiovascular disorders from radiology scans requires quantitative image analysis of the heart and its substructures. There are well-established measurements that radiologists use for diseases assessment such as ejection fraction, volume of four chambers, and myocardium mass. These measuremen…
A new method combines OCSVM with representation learning for UAD.
problem Detect anomalies without labeled data, especially in rare or unavailable cases.
method Custom loss formulation that aligns latent features with OCSVM decision boundary.
result Succeeds in detecting small, non-hyperintense lesions in MRI.
The paper uses distance correlation for brain connectivity and a novel multi-task learning model for age prediction.
problem Estimating age-related gender differences in brain functional connectivity.
method Estimates functional connectivity using distance correlation and proposes a non-convex multi-task learning model.
result The proposed non-convex multi-task learning model outperforms other models in age prediction and gender-specific connectivity.
Unified method for input, data, and model uncertainty in neural networks.
problem Uncertainty in neural network inputs and outputs.
method Propagating uncertainty through inputs using a unified formulation.
result More stable decision boundaries with input noise, and propagation of input uncertainty to model outputs.
This paper benchmarks uncertainty disentanglement across various tasks.
problem Disentangling multiple sources of uncertainty for specialized tasks.
method Reimplemented and evaluated a wide range of uncertainty estimators.
result No existing approach provides disentangled uncertainty estimators in practice.
Unified Bayesian framework for quantifying GNN uncertainty.
problem Quantifying uncertainty in GNN predictions due to modeling errors and measurement uncertainty.
method Unified Bayesian framework with aleatoric uncertainty from probabilistic links and feature noise, and epistemic uncertainty from model parameter distribution. Uses Assumed Density Filtering for aleatoric uncertainty and Monte Carlo dropout for model parameter uncertainty.
result Bayesian model performs similarly to frequentist model and provides additional uncertainty information.
Paper recovers uncertainty from dynamic valuation rules.
problem Recovering latent uncertainty from observable valuation rules.
method Developed procedures to identify and characterize uncertainty structures from valuation rules.
result Valuation rules contain sufficient information to identify and recover uncertainty structures.
Proposes a new criterion for reliable uncertainty estimation in deep neural networks.
problem Inability of existing approaches to provide reliable uncertainty estimates for deep neural networks.
method Develops a density uncertainty layer architecture that satisfies the proposed criterion.
result Density uncertainty layers provide more reliable uncertainty estimates and robust out-of-distribution detection.
Proposes a method to quantify uncertainty in graph neural networks for node classification.
problem Uncertainty in graph neural networks for node classification.
method Bayesian uncertainty propagation (BUP) method embedding GNNs in a Bayesian framework.
result Demonstrates superior performance of the proposed method on benchmark datasets.
A framework for estimating both epistemic and aleatoric uncertainties in reinforcement learning.
problem Estimating risk and uncertainty in deep reinforcement learning.
method Proposed a framework for disentangling and estimating epistemic and aleatoric uncertainties on learned Q-values, derived unbiased estimators, and introduced an uncertainty-aware DQN algorithm.
result The uncertainty-aware DQN algorithm exhibits safe learning behavior and outperforms other DQN variants on the MinAtar testbed.
Survey on uncertainty in ML and DL, covering sources, quantification, and decision-making.
problem Understanding and quantifying uncertainty in ML and DL for risk-sensitive applications.
method Structured review of literature, categorizing uncertainty, assessing uncertainty quantification techniques.
result Broadened scope of uncertainty discussion and updated DL uncertainty quantification methods.
Unified Uncertainty Calibration improves AI predictions by combining different types of uncertainty.
problem AI classifiers struggle with uncertainty, leading to miscalibrated predictions and poor performance.
method Unified Uncertainty Calibration (U2C) combines aleatoric and epistemic uncertainties to improve prediction quality.
result U2C outperforms traditional reject-or-classify methods across various ImageNet benchmarks.
Proposes a new principle for active learning based on epistemic uncertainty.
problem Active learning and uncertainty quantification in machine learning.
method Distinction between epistemic and aleatoric uncertainty; proposes epistemic uncertainty sampling.
result Epistemic uncertainty sampling shows promising performance in experimental studies.
New method combines ODE filters and numerical quadrature to propagate model uncertainty.
problem Propagation of model uncertainty in ODE solutions with uncertain parameters.
method Combining ODE filters with numerical quadrature.
result Effective propagation of both numerical and parametric uncertainty.
Paper decomposes risk into aleatoric and epistemic uncertainties and generates predictive uncertainty measures.
problem Unclear relationships between various predictive uncertainty measures in literature.
method Bayesian estimation to decompose risk into aleatoric and epistemic uncertainties, generating different predictive uncertainty measures.
result Experimental validation confirms usefulness of derived predictive uncertainty measures for detecting out-of-distribution and misclassified instances.
Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Differe…
New method estimates model uncertainty in regression.
problem Challenges in distinguishing aleatoric and epistemic uncertainty.
method Conditional predictions with model's initial output.
result Rigorous frequentist approach to epistemic uncertainty.
Introduces hierarchical uncertainty using U-sequences.
problem Tackles Ellsberg's paradox in multi-layer uncertainty.
method Uses category theory to construct U-sequences and endofunctors.
result Constructs a universal uncertainty space for multi-layer uncertainty.
Connects robust optimization to conformal prediction for uncertainty sets.
problem Decision-making under uncertainty in sensitive data.
method Defines Mahalanobis distance as a conformity score and generates conformal uncertainty sets.
result Conformal uncertainty sets provide valid and conservative ellipsoidal regions.
We propose orthogonality as a necessary condition for disentangling aleatoric and epistemic uncertainty.
problem Jointly estimating aleatoric and epistemic uncertainty is problematic and non-trivial.
method We propose orthogonality as a necessary condition for disentanglement and construct UDE to measure orthogonality and consistency.
result Orthogonality and consistency are necessary and sufficient criteria for disentanglement.
New method RECAST improves uncertainty calibration in neural networks.
problem Improving uncertainty estimation in neural networks for better predictions.
method Proposed RECAST method combining cosine annealing, warm restarts, and Stochastic Gradient Langevin Dynamics.
result RECAST offers the best calibrated measure of uncertainty compared to recent methods.
This work introduces a method to decompose uncertainty in in-context learning for large language models.
problem Understanding the sources of uncertainty in in-context learning for large language models.
method Variational uncertainty decomposition framework without sampling from latent parameter posterior.
result Quantitative and qualitative validation of decomposed epistemic and aleatoric uncertainties.
Cooperative model disentangles data uncertainties.
problem Disentangling aleatoric and epistemic uncertainties in real-world data.
method Cooperatively trains a variance estimation network with a Bayesian neural network.
result Improves mean estimation and disentangles uncertainties.
Framework disentangles deep feature uncertainty for efficient inference.
problem Inference-time uncertainty estimation for reliable decision-making.
method Uncertainty-Guided Inference-Time Selection framework.
result Significantly tighter prediction intervals and 60% compute reduction.
This study introduces axioms to assess regression uncertainty measures.
problem Limited formal justification and evaluations of uncertainty measures in regression settings.
method Introduces axioms and analyzes entropy- and variance-based measures in a predictive exponential family context.
result Provides a principled foundation for reliable uncertainty assessment in regression.
Study improves AI's handling of uncertainty.
problem Uncertainty in AI models, especially with limited data.
method Integrates theories, latest developments, and practical applications.
result Novel definition of total uncertainty in AI.
Develops a framework to quantify uncertainties in multiple ML models.
problem Uncertainty in ML model predictions and model inputs.
method Develops a theoretical framework to decouple and transform uncertainties.
result Generates joint distribution of ML predictions considering uncertainties.
Second-order methods fail to fully quantify epistemic uncertainty, leading to biased predictions.
problem Incomplete quantification of epistemic uncertainty in machine learning models.
method Analysis of existing second-order uncertainty estimation methods.
result Current methods overestimate aleatoric uncertainty and underestimate epistemic uncertainty, leading to biased predictions.
Bayesian inference improves neural network predictions by separating aleatoric and epistemic uncertainties.
problem Improving prediction accuracy of neural networks by quantifying and separating uncertainties.
method Approximated posterior distributions using deep ensembles for various neural network architectures.
result Prediction accuracy depends on both aleatoric and epistemic uncertainties, not just marginalized uncertainty.
New method improves estimation of neural network aleatoric uncertainty.
problem Existing methods overestimate aleatoric uncertainty in neural networks.
method Proposes a new de-noising method to estimate data uncertainty more accurately.
result Demonstrates better approximation of actual data uncertainty.
New method explains sensitivity of test data uncertainty in Bayesian inference.
problem Widespread belief that test data similarity reduces epistemic uncertainty.
method Information-theoretic decomposition of predictive uncertainty.
result Defines sensitivity using information-theoretic quantities.
This paper tackles uncertainty in deep learning for construction of prediction intervals.
problem Deep learning models lack the ability to provide reliable prediction intervals for high-risk tasks.
method The authors design a special loss function to learn both aleatory and epistemic uncertainties without requiring uncertainty labels.
result The method constructs prediction intervals that are competitive with state-of-the-art methods on publicly available datasets.
This paper examines sources of uncertainty in machine learning from a statistical perspective.
problem Quantifying uncertainty in supervised machine learning models.
method A conceptual, basic science approach examining aleatoric and epistemic uncertainty.
result Sources of uncertainty are diverse and cannot always be decomposed into aleatoric and epistemic.
Framework for quantifying uncertainty in dynamic processes.
problem Quantifying uncertainty in dynamic stochastic processes.
method Define dynamic uncertainty sets and dynamic robust risk measures.
result Dynamic robust risk measures are time-consistent under specific uncertainty sets.
Study decomposes uncertainty in HK-distribution parameter estimation for QUS.
problem Uncertainty in HK-distribution parameter estimation for quantitative ultrasound.
method Bayesian Neural Networks (BNNs) for parameter estimation and uncertainty decomposition.
result Decomposes total predictive uncertainty into epistemic and aleatoric components.
This paper uses a diffusion model to forecast electrical loads with uncertainty.
problem Uncertainties in electrical load forecasting due to renewable energy and external events.
method Diffusion-based Seq2Seq structure for epistemic uncertainty and robust additive Cauchy distribution for aleatoric uncertainty.
result Ability to separate and quantify both types of uncertainties in load forecasting.