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...

You might also read

Related Articles

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

Sort by

Same author

A voxel-wise uncertainty-guided framework for glioma segmentation using spherical projection-based U-Net and localized refinement.

Medical physics·2026

Same author

PhysMorph: A biomechanical and image-guided deep learning framework for real-time multi-modal liver image registration.

Physics and imaging in radiation oncology·2026

Same author

An exploratory study on integrating radiomics with vision transformers for enhancing medical imaging classification accuracy.

Medical physics·2026

Same author

Knowledge-based deep residual U-Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery.

Journal of applied clinical medical physics·2025

Same author

An Implicit Registration Framework Integrating Kolmogorov-Arnold Networks with Velocity Regularization for Image-Guided Radiation Therapy.

Bioengineering (Basel, Switzerland)·2025

Same author

Finite Element Method-Based Hybrid MRI/CBCT Generation to Improve Liver Stereotactic Body Radiation Therapy Targets Localization Accuracy.

IEEE transactions on radiation and plasma medical sciences·2025

Same journal

MELF: A multi-view ensemble learning framework for normative resting state EEG signal quality assessment.

Biomedical physics & engineering express·2026

Same journal

Rhythm-adaptive signal processing for effective ECG and PPG-based authentication under dynamic physiological conditions.

Biomedical physics & engineering express·2026

Same journal

Influence of storage temperature and humidity on entrance window deformations of phantoms for a horizontal beam geometry.

Biomedical physics & engineering express·2026

Same journal

Metamaterial-loaded waveguide antenna with integrated gradient-index cooling lens for abdominal subcutaneous adipose ablation.

Biomedical physics & engineering express·2026

Same journal

Adaptive deformation decomposition network for unsupervised medical image registration.

Biomedical physics & engineering express·2026

Same journal

Beyond the tumor: Recurrence-prone radiomics for prognostication in negative PSMA PET/CT scans of prostate cancer.

Biomedical physics & engineering express·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 24, 2025

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

A geometry-guided multi-beamlet deep learning technique for CT reconstruction.

Ke Lu^1,2, Lei Ren³, Fang-Fang Yin^1,2,4

¹Medical Physics Graduate Program, Duke University, Durham, NC, United States of America.

Biomedical Physics & Engineering Express

|May 5, 2022

Summary

This summary is machine-generated.

A novel Geometry-guided Multi-beamlet Deep Learning (GMDL) technique significantly improves low-dose CT image reconstruction. GMDL achieves superior image quality and drastically reduces model size and memory needs compared to traditional methods.

Keywords:

CT deep learning fully connected layer reconstruction

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

Related Experiment Videos

Last Updated: Sep 24, 2025

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

Area of Science:

Medical Imaging
Deep Learning
Computational Imaging

Background:

Deep learning methods for CT image reconstruction often use large fully-connected layers, leading to high computational demands and memory usage.
Previous Geometry-guided Deep Learning (GDL) reduced model size but can be further optimized.
Low-dose CT reconstruction is crucial for reducing patient radiation exposure while maintaining diagnostic image quality.

Purpose of the Study:

To introduce and evaluate a novel Geometry-guided Multi-beamlet Deep Learning (GMDL) technique for enhanced low-dose CT image reconstruction.
To compare the performance of GMDL against Fully-connected layer Deep Learning (FCDL), GDL, and Filtered Back Projection (FBP) methods.
To assess the impact of GMDL on image quality, model size, and GPU memory consumption.

Main Methods:

Developed GMDL by replacing large fully-connected layers with multiple smaller ones that learn projection-to-image transformation.
GMDL connects projection pixels to multiple beamlets (central and peripheral) in the image domain, guided by CT geometry.
Quantitative analysis using Peak-Signal-to-Noise-Ratio (PSNR), Structural-Similarity-Index-Measure (SSIM), and Root-Mean-Square-Error (RMSE) on real-patient low-dose CT data.

Main Results:

GMDL demonstrated superior image reconstruction quality compared to FCDL, GDL, and FBP, evidenced by improved PSNR, SSIM, and RMSE values.
The optimal GMDL configuration utilized two peripheral beamlets on each side of the central beamlet.
GMDL achieved a reduction in model size and memory consumption to less than 1/100th of the FCDL model.

Conclusions:

The GMDL technique offers a significant advancement in low-dose CT image reconstruction.
GMDL provides improved image quality over FCDL while substantially decreasing computational resource requirements.
This method holds promise for more efficient and effective low-dose CT imaging in clinical practice.