Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Computed Tomography

Computed Tomography

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...

Imaging Studies I: CT and MRI

Imaging Studies I: CT and MRI

Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...

You might also read

Related Articles

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

Sort by

Same author

Comprehensive evaluation of a deep learning-based synthetic CT model for MR-only radiotherapy across multiple anatomical sites.

Physics and imaging in radiation oncology·2026

Same author

Toward universal dose prediction: A multi-scale, multi-objective framework for sequential boost radiotherapy.

Medical physics·2026

Same author

Strategies for enhancing delivery efficiency on MR-Linac: A dosimetric study and historical plan review.

Journal of applied clinical medical physics·2026

Same author

RAPID-LC: rapid evidence-to-practice uptake of large core thrombectomy across a stroke consortium.

Journal of neurology·2026

Same author

Reply: Why fan therapy does not yet demonstrate enhanced training benefits in people with chronic respiratory disease.

The European respiratory journal·2026

Same author

A Simulation-Free Radiation Therapy Workflow Using Synthetic Computed Tomography Generated from Diagnostic Magnetic Resonance Imaging for Personalized Hippocampal-Sparing Whole-Brain Treatment.

Practical radiation oncology·2026

Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026

Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026

Same journal

A novel optical respiratory gating system with a hybrid phase-amplitude algorithm for spot-scanning proton therapy.

Medical physics·2026

Same journal

Gamma Knife treatment planning using knowledge-based reinforcement learning.

Medical physics·2026

Same journal

Development and characterization of a novel, small animal external beam irradiator using a clinical high dose rate brachytherapy source.

Medical physics·2026

Same journal

Deep learning-based dose prediction for MR-guided prostate SIB: Supporting rapid feasibility assessment and adaptive editing margin selection.

Medical physics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 16, 2025

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

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

Published on: April 13, 2013

Probabilistic self-learning framework for low-dose CT denoising.

Ti Bai¹, Biling Wang¹, Dan Nguyen¹

¹Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Centre, Dallas, Texas, 75239, USA.

Medical Physics

|February 23, 2021

Summary

This summary is machine-generated.

This study introduces a novel deep learning method for low-dose CT (LDCT) denoising, addressing data scarcity by using only LDCT images. The probabilistic self-learning (PSL) framework effectively reduces noise while preserving image details, outperforming existing methods.

Keywords:

CT deep learning denoise self-learning

More Related Videos

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Nov 16, 2025

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

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

Published on: April 13, 2013

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

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

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

X-ray computed tomography (CT) is crucial in diagnostics but poses risks due to ionizing radiation.
Reducing radiation dose in CT (low-dose CT or LDCT) lowers risks but increases image noise.
Deep learning for LDCT denoising typically requires large paired datasets of LDCT and normal-dose CT (NDCT) images, which are scarce in clinical practice.

Purpose of the Study:

To mitigate the data scarcity problem in deep learning-based LDCT image denoising.
To develop a method that can denoise LDCT images effectively without requiring paired normal-dose images.

Main Methods:

A novel shift-invariant property-based neural network, termed probabilistic self-learning (PSL), was developed.
The PSL framework utilizes only LDCT images to learn inherent pixel correlations and noise distribution.
Performance was evaluated against conventional (TV-based) and other deep learning methods (N2V, CycleGAN) using simulated and real datasets, with quantitative metrics (PSNR, SSIM, CNR) and visual inspection.

Main Results:

The PSL method significantly improved averaged PSNR/SSIM values from 27.61/0.5939 (LDCT) to 30.50/0.6797.
PSL achieved lower standard deviations in flat regions (60.62 HU) compared to LDCT (132.3 HU) and CycleGAN (75.06 HU), indicating better noise reduction.
Qualitative assessment showed PSL preserved details while suppressing noise, unlike TV (blocky artifacts), N2V (over-smoothing, bias), or CycleGAN (noise, inaccurate CT values). PSL also demonstrated generalizability across datasets.

Conclusions:

A deep learning convolutional neural network can be trained for LDCT denoising without paired datasets.
The proposed PSL method demonstrates superior denoising performance compared to competing methods through qualitative visual inspection.
While quantitative metrics like PSNR, SSIM, and CNR did not consistently show superior values, the overall denoising quality and detail preservation were enhanced.