Related Experiment Video
Updated: Jun 12, 2025
09:09
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
411
Uncertainty estimation for trust attribution to speed-of-sound reconstruction with variational networks
Sonia Laguna1, Lin Zhang1, Can Deniz Bezek2
1Computer-assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland.
Summary
Uncertainty estimation in speed-of-sound imaging helps select the best ultrasound frame for diagnosing breast cancer. This method improves accuracy in distinguishing benign from malignant lesions.
Area of Science:
- Medical imaging
- Biomedical engineering
- Machine learning
Background:
- Speed-of-sound (SoS) imaging offers a promising diagnostic biomarker.
- Variational networks are effective for SoS reconstruction from ultrasound data.
- Noisy ultrasound frames can degrade SoS image quality and diagnostic accuracy.
Purpose of the Study:
- To develop an uncertainty-based method for selecting reliable ultrasound frames for SoS imaging.
- To improve diagnostic decisions by retrospectively choosing the most trustworthy data acquisition.
- To enhance the accuracy of SoS-based breast cancer diagnosis.
Main Methods:
- Utilizing uncertainty estimation in SoS reconstructions to evaluate individual ultrasound frames.
- Implementing automatic frame selection based on uncertainty quantification.
- Investigating Monte Carlo Dropout and Bayesian Variational Inference for uncertainty estimation.
Main Results:
- The uncertainty-based frame selection method was evaluated for differentiating benign fibroadenoma from malignant carcinoma in BI-RADS 4 breast lesions.
- The best frame identified using uncertainty criteria improved the area under the curve (AUC) to 76% (Monte Carlo Dropout) and 80% (Bayesian Variational Inference).
- These results significantly outperformed uncertainty-uninformed baselines, which achieved a best AUC of 64%.
Conclusions:
- A novel application of uncertainty estimation is presented for selecting optimal data acquisitions in medical imaging.
- This approach enhances the reliability of SoS imaging for clinical decision-making.
- The proposed method shows potential for improving the diagnostic performance in breast cancer assessment.
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
00:59Propagation of Uncertainty from Random Error
655
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...
655
01:10Propagation of Uncertainty from Systematic Error
489
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...
489
00:59Uncertainty: Overview
528
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.
528
01:09Deriving the Speed of Sound in a Liquid
482
As with waves on a string, the speed of sound or a mechanical wave in a fluid depends on the fluid's elastic modulus and inertia. The two relevant physical quantities are the bulk modulus and the density of the material. Indeed, it turns out that the relationship between speed and the bulk modulus and density in fluids is the same as that between the speed and the Young's modulus and density in solids.
The speed of sound in fluids can be derived by considering a mechanical wave...
The speed of sound in fluids can be derived by considering a mechanical wave...
482
01:05Estimation of the Physical Quantities
4.2K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
4.2K