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

Computed Tomography01:10

Computed Tomography

6.4K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.4K
Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

59
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
59

You might also read

Related Articles

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

Sort by
Same author

CMR Predictors of Liver Cirrhosis by MRI in a National Paediatric Fontan Cohort.

European heart journal. Cardiovascular Imaging·2026
Same author

Influence of radiation field size on half-value layer measurements in mammography.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same author

Occupational radiation doses in CT-guided interventions: A multicentre evaluation with special emphasis on lung biopsies and eye lens doses.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same author

Impact of coronary artery disease on systolic function in severe aortic stenosis-a multimodality imaging study.

European heart journal. Imaging methods and practice·2026
Same author

European Multicentre Study on Recurrent Imaging Practice in Computed Tomography.

The British journal of radiology·2026
Same author

CMR T1 and T2 mapping and extracellular volume quantification in systolic phase produces superior image quality with less motion artifacts and equal mapping values compared to conventional diastolic mapping.

Magma (New York, N.Y.)·2026

Related Experiment Video

Updated: Sep 20, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Automatic head computed tomography image noise quantification with deep learning.

Satu I Inkinen1, Teemu Mäkelä2, Touko Kaasalainen1

  • 1HUS Diagnostic Center, Radiology, Helsinki University and Helsinki University Hospital, Haartmaninkatu 4, 00290 Helsinki, Finland.

Physica Medica : PM : an International Journal Devoted to the Applications of Physics to Medicine and Biology : Official Journal of the Italian Association of Biomedical Physics (AIFB)
|June 7, 2022
PubMed
Summary
This summary is machine-generated.

Deep learning (DL) accurately estimates computed tomography (CT) image noise using convolutional neural networks (CNNs). The noise2noise approach shows promise for clinical applications without ground truth data.

Keywords:
Anthropomorphic phantomBrainComputed tomographyDeep learningImage qualityNoise

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
06:45

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

Published on: June 2, 2023

1.8K

Related Experiment Videos

Last Updated: Sep 20, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
06:45

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

Published on: June 2, 2023

1.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Image Processing

Background:

  • Computed tomography (CT) image noise is conventionally quantified using the standard deviation (SD) of pixel values in uniform regions.
  • Accurate noise estimation is crucial for reliable image interpretation and quality assessment in CT scans.
  • Traditional methods may not fully capture the complexities of noise in low-dose CT images.

Purpose of the Study:

  • To investigate the application of deep learning (DL) techniques for estimating noise in head CT images.
  • To compare the accuracy of different DL architectures and training approaches for noise estimation.
  • To evaluate the feasibility of DL-based noise assessment in clinical settings.

Main Methods:

  • Two DL approaches were explored: direct noise estimation using a supervised deep convolutional neural network (DnCNN) and image subtraction using a denoising UNet-CNN with supervised and unsupervised noise2noise training.
  • Noise was assessed using local SD maps with 3D- and 2D-CNN architectures on anthropomorphic phantom and open-source clinical head CT datasets.
  • Performance was evaluated using mean square error (MSE) and mean absolute percentage errors (MAPE) against ground truth SD values.

Main Results:

  • The direct SD estimation using a 3D-CNN achieved the highest accuracy on the phantom dataset (MAPE = 15.5%, MSE = 6.3 HU).
  • The unsupervised noise2noise approach yielded slightly inferior results (MAPE = 20.2%, MSE = 13.7 HU).
  • 2D-CNN and unsupervised UNet models demonstrated the lowest MSE on clinically labeled uniform regions.

Conclusions:

  • Deep learning-based clinical image noise assessment is feasible and offers acceptable accuracy compared to true image noise.
  • The noise2noise approach is a viable option for clinical use when ground truth data is unavailable.
  • Integrating noise estimation with tissue segmentation can lead to more comprehensive characterization of image quality.