Uncertainty Aware Training to Improve Deep Learning Model Calibration
for Classification of Cardiac MR Images
- URL: http://arxiv.org/abs/2308.15141v1
- Date: Tue, 29 Aug 2023 09:19:49 GMT
- Title: Uncertainty Aware Training to Improve Deep Learning Model Calibration
for Classification of Cardiac MR Images
- Authors: Tareen Dawood, Chen Chen, Baldeep S. Sidhua, Bram Ruijsink, Justin
Goulda, Bradley Porter, Mark K. Elliott, Vishal Mehta, Christopher A.
Rinaldi, Esther Puyol-Anton, Reza Razavi, Andrew P. King
- Abstract summary: Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy AI models.
We evaluate three novel uncertainty-aware training strategies comparing against two state-of-the-art approaches.
- Score: 3.9402047771122812
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Quantifying uncertainty of predictions has been identified as one way to
develop more trustworthy artificial intelligence (AI) models beyond
conventional reporting of performance metrics. When considering their role in a
clinical decision support setting, AI classification models should ideally
avoid confident wrong predictions and maximise the confidence of correct
predictions. Models that do this are said to be well-calibrated with regard to
confidence. However, relatively little attention has been paid to how to
improve calibration when training these models, i.e., to make the training
strategy uncertainty-aware. In this work we evaluate three novel
uncertainty-aware training strategies comparing against two state-of-the-art
approaches. We analyse performance on two different clinical applications:
cardiac resynchronisation therapy (CRT) response prediction and coronary artery
disease (CAD) diagnosis from cardiac magnetic resonance (CMR) images. The
best-performing model in terms of both classification accuracy and the most
common calibration measure, expected calibration error (ECE) was the Confidence
Weight method, a novel approach that weights the loss of samples to explicitly
penalise confident incorrect predictions. The method reduced the ECE by 17% for
CRT response prediction and by 22% for CAD diagnosis when compared to a
baseline classifier in which no uncertainty-aware strategy was included. In
both applications, as well as reducing the ECE there was a slight increase in
accuracy from 69% to 70% and 70% to 72% for CRT response prediction and CAD
diagnosis respectively. However, our analysis showed a lack of consistency in
terms of optimal models when using different calibration measures. This
indicates the need for careful consideration of performance metrics when
training and selecting models for complex high-risk applications in healthcare.
Related papers
- Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Training [2.0006125576503617]
We evaluate the impact on accuracy and calibration of two types of approach that aim to improve deep learning (DL) classification model calibration.
Specifically, we test the performance of three DUMs and two uncertainty-aware training approaches as well as their combinations.
Our results indicate that both DUMs and uncertainty-aware training can improve both accuracy and calibration in both of our applications.
arXiv Detail & Related papers (2024-05-10T14:07:58Z) - Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance.
We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
arXiv Detail & Related papers (2024-02-13T11:25:20Z) - Uncertainty Quantification on Clinical Trial Outcome Prediction [37.238845949535616]
We propose incorporating uncertainty quantification into clinical trial outcome predictions.
Our main goal is to enhance the model's ability to discern nuanced differences.
We have adopted a selective classification approach to fulfill our objective.
arXiv Detail & Related papers (2024-01-07T13:48:05Z) - Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty [52.03490691733464]
We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.
By leveraging subjective logic theory, we explicitly model probability and uncertainty for the problem of medical image segmentation.
DeviS incorporates an uncertainty-aware filtering module, which utilizes the metric of uncertainty-calibrated error to filter reliable data.
arXiv Detail & Related papers (2023-01-01T05:02:46Z) - Uncertainty estimations methods for a deep learning model to aid in
clinical decision-making -- a clinician's perspective [0.0]
There are several deep learning-inspired uncertainty estimation techniques, but few are implemented on medical datasets.
We compared dropout variational inference (DO), test-time augmentation (TTA), conformal predictions, and single deterministic methods for estimating uncertainty.
It may be important to evaluate multiple estimations techniques before incorporating a model into clinical practice.
arXiv Detail & Related papers (2022-10-02T17:54:54Z) - Density-Aware Personalized Training for Risk Prediction in Imbalanced
Medical Data [89.79617468457393]
Training models with imbalance rate (class density discrepancy) may lead to suboptimal prediction.
We propose a framework for training models for this imbalance issue.
We demonstrate our model's improved performance in real-world medical datasets.
arXiv Detail & Related papers (2022-07-23T00:39:53Z) - BSM loss: A superior way in modeling aleatory uncertainty of
fine_grained classification [0.0]
We propose a modified Bootstrapping loss(BS loss) function with Mixup data augmentation strategy.
Our experiments indicated that BS loss with Mixup(BSM) model can halve the Expected Error(ECE) compared to standard data augmentation.
BSM model is able to perceive the semantic distance of out-of-domain data, demonstrating high potential in real-world clinical practice.
arXiv Detail & Related papers (2022-06-09T13:06:51Z) - Performance or Trust? Why Not Both. Deep AUC Maximization with
Self-Supervised Learning for COVID-19 Chest X-ray Classifications [72.52228843498193]
In training deep learning models, a compromise often must be made between performance and trust.
In this work, we integrate a new surrogate loss with self-supervised learning for computer-aided screening of COVID-19 patients.
arXiv Detail & Related papers (2021-12-14T21:16:52Z) - Uncertainty-Aware Training for Cardiac Resynchronisation Therapy
Response Prediction [3.090173647095682]
Quantifying uncertainty of a prediction is one way to provide such interpretability and promote trust.
We quantify the data (aleatoric) and model (epistemic) uncertainty of a DL model for Cardiac Resynchronisation Therapy response prediction from cardiac magnetic resonance images.
We perform a preliminary investigation of an uncertainty-aware loss function that can be used to retrain an existing DL image-based classification model to encourage confidence in correct predictions.
arXiv Detail & Related papers (2021-09-22T10:37:50Z) - UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced
Data [81.00385374948125]
We present UNcertaInTy-based hEalth risk prediction (UNITE) model.
UNITE provides accurate disease risk prediction and uncertainty estimation leveraging multi-sourced health data.
We evaluate UNITE on real-world disease risk prediction tasks: nonalcoholic fatty liver disease (NASH) and Alzheimer's disease (AD)
UNITE achieves up to 0.841 in F1 score for AD detection, up to 0.609 in PR-AUC for NASH detection, and outperforms various state-of-the-art baselines by up to $19%$ over the best baseline.
arXiv Detail & Related papers (2020-10-22T02:28:11Z) - Learning to Predict Error for MRI Reconstruction [67.76632988696943]
We demonstrate that predictive uncertainty estimated by the current methods does not highly correlate with prediction error.
We propose a novel method that estimates the target labels and magnitude of the prediction error in two steps.
arXiv Detail & Related papers (2020-02-13T15:55:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.