Related Experiment Video
Updated: Jun 12, 2025
07:13
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023
1.1K
Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles
William C Walton1,2, Seung-Jun Kim3
1University of Maryland, Baltimore County, CSEE Department, Baltimore, MD, 21250, USA.
Journal of Imaging Informatics in Medicine
|September 23, 2024
Summary
New deep learning methods provide uncertainty estimates for registering breast cancer lesions across mammogram views. These confidence scores help clinicians assess lesion correspondence, improving diagnostic accuracy, especially in dense breast tissue.
Area of Science:
- Medical imaging analysis
- Artificial intelligence in radiology
- Machine learning for diagnostics
Background:
- Accurate lesion correspondence between craniocaudal (CC) and mediolateral oblique (MLO) mammographic views is crucial for clinical diagnosis.
- Automated registration tools can assist clinicians, but lack confidence estimates, limiting their utility in challenging cases like dense breast tissue.
- Convolutional neural network (CNN)-based methods are used for lesion registration, but quantifying their uncertainty is essential for clinical trust.
Purpose of the Study:
- To develop and evaluate uncertainty estimation techniques for CNN-based lesion registration in mammography.
- To enhance the clinical utility of automated registration tools by providing confidence measures for multi-view lesion correspondence.
- To improve diagnostic capabilities by aiding clinicians in confidently identifying and correlating lesions across different mammographic views.
Main Methods:
- Implementation of deep ensemble-based techniques utilizing a negative log-likelihood (NLL) cost function for uncertainty estimation.
- Modification of an existing CNN dual-view lesion registration algorithm with three distinct ensemble architectures.
- Evaluation of different ensemble sizes and performance metrics on synthetic, real 2D, and real 3D X-ray mammographic data.
Main Results:
- Ensemble methods generated covariance-based uncertainty ellipses correlated with registration accuracy.
- Ellipse sizes provide clinicians with a quantifiable indication of confidence in the CC-MLO view mapping.
- Uncertainty estimates aided in improving computer-aided detection (CAD) by matching lesion detections and reducing false alarms.
Conclusions:
- The developed uncertainty estimation techniques show significant promise for clinical application in mammography.
- These methods can empower clinicians to confidently establish multi-view lesion correspondence, enhancing diagnostic accuracy.
- Improved lesion registration confidence has the potential to refine computer-aided detection systems and reduce diagnostic errors.
Related Concept Videos
00:54Uncertainty: Confidence Intervals
3.1K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
3.1K
00:59Uncertainty: Overview
529
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
529
03:37Uncertainty in Measurement: Accuracy and Precision
73.5K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
73.5K
00:59Propagation of Uncertainty from Random Error
656
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
656
01:10Propagation of Uncertainty from Systematic Error
490
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
490