Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

1.0K
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...
1.0K
Propagation of Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

1.3K
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...
1.3K
Uncertainty: Overview00:59

Uncertainty: Overview

1.2K
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.
1.2K
Uncertainty: Confidence Intervals00:54

Uncertainty: Confidence Intervals

7.1K
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...
7.1K
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.4K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multimodal Deep Learning for Prediction of Progression-Free Survival in Patients with Neuroendocrine Tumors Undergoing <sup>177</sup>Lu-Based Peptide Receptor Radionuclide Therapy.

Cancers·2026
Same author

Software for dataset-wide XAI: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy.

PloS one·2026
Same author

Investigation of data-driven stopping power calibration of treatment planning x-ray CT from simulated sparse-view proton radiographies.

Physics in medicine and biology·2025
Same author

The EUROCROPSML time series benchmark dataset for few-shot crop type classification in Europe.

Scientific data·2025
Same author

On opportunities and challenges of large multimodal foundation models in education.

NPJ science of learning·2025
Same author

Discovering Subgroups of Children With High Mortality in Urban Guinea-Bissau: Exploratory and Validation Cohort Study.

JMIR public health and surveillance·2024

Related Experiment Video

Updated: Oct 21, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Detecting failure modes in image reconstructions with interval neural network uncertainty.

Luis Oala1, Cosmas Heiß2, Jan Macdonald2

  • 1Department of Artificial Intelligence, Fraunhofer HHI, Berlin, Germany. luis.oala@hhi.fraunhofer.de.

International Journal of Computer Assisted Radiology and Surgery
|September 4, 2021
PubMed
Summary

Interval Neural Networks (INNs) provide a lightweight method for detecting deep neural network failures in image reconstruction. These networks quantify uncertainty, improving reliability and aiding in the deployment of AI models.

Keywords:
Deep learningFailure modesImage reconstructionUncertainty quantification

Related Experiment Videos

Last Updated: Oct 21, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Deep neural networks (DNNs) are increasingly used in image reconstruction, but their reliability at scale is challenged by failure modes.
  • Quantitative detection of these failures is crucial for dependable DNN deployment.

Purpose of the Study:

  • To introduce uncertainty quantification as a fine-grained alarm system for DNNs in image reconstruction.
  • To demonstrate the effectiveness of Interval Neural Networks (INNs) in identifying common failure modes.

Main Methods:

  • Proposed a deterministic, modular, and lightweight approach called Interval Neural Network (INN).
  • INNs generate fast and interpretable uncertainty scores for DNNs.
  • INNs can be applied post hoc to already trained networks and compared against MCDROP and PROBOUT.

Main Results:

  • INNs effectively capture uncertainty from noise and directional error information in synthetic inverse problems.
  • On real-world CT scan data, INNs significantly improved the detection of failure modes compared to baseline methods.
  • Uncertainty scores from INNs enhance the reliability of image reconstruction models.

Conclusions:

  • Interval Neural Networks present a promising tool for exposing weaknesses in deep image reconstruction models.
  • The post hoc applicability of INNs makes them particularly valuable for deploying reliable DNNs.