Search Results for author:
Found 10 papers, 6 papers with code
Improving the repeatability of deep learning models with Monte Carlo dropout
During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice.
QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation.
Monte Carlo dropout increases model repeatability
Leveraging Monte Carlo predictions significantly increased repeatability for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 17% points.
Fair Conformal Predictors for Applications in Medical Imaging
Deep learning has the potential to automate many clinically useful tasks in medical imaging.
Evaluating subgroup disparity using epistemic uncertainty in mammography
As machine learning (ML) continue to be integrated into healthcare systems that affect clinical decision making, new strategies will need to be incorporated in order to effectively detect and evaluate subgroup disparities to ensure accountability and generalizability in clinical workflows.
Addressing catastrophic forgetting for medical domain expansion
Notably, this approach degrades model performance at the original institution, a phenomenon known as catastrophic forgetting.
The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions
Model brittleness is a primary concern when deploying deep learning models in medical settings owing to inter-institution variations, like patient demographics and intra-institution variation, such as multiple scanner types.
Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging
Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image.
Give me (un)certainty -- An exploration of parameters that affect segmentation uncertainty
We assess the utility of three measures of uncertainty (Coefficient of Variation, Mean Pairwise Dice, and Mean Voxelwise Uncertainty) for the segmentation of a less ambiguous target structure (liver) and a more ambiguous one (liver tumors).
DeepNeuro: an open-source deep learning toolbox for neuroimaging
Translating neural networks from theory to clinical practice has unique challenges, specifically in the field of neuroimaging.
