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 Experiment Video

Updated: Jan 11, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729

Deep learning based medical image compression using cross attention learning and wavelet transform.

Fan Dai1

  • 1School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, Shaanxi, China. dfan@mail.nwpu.edu.cn.

Scientific Reports
|November 14, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Two decades of methane budgets at the sub-national scale in China.

Science bulletin·2026
Same author

Mucoadhesive Nanothalidomide Enema: Simultaneous Radioprotection and Barrier Repair in Radiation Enteritis Therapy.

ACS nano·2026
Same author

Engineering NIR-II carbon dots through aniline extension with graphene and nitrogen enrichment for hepatobiliary theranostics.

Nature communications·2026
Same author

Electroacupuncture improves hypoxic stress and energy metabolism to alleviate vascular cognitive impairment through activation of the HIF-1α/p53/NGB signaling pathway in rats.

Iranian journal of basic medical sciences·2026
Same author

Magnetic anomaly detection method based on principal component analysis and cascaded stochastic resonance.

The Review of scientific instruments·2026
Same author

DUSP1 interacts with BIP to regulate Staphylococcus aureus-induced apoptosis through the MAPK signaling pathway.

Microbiological research·2025
Same journal

A tri-axis optomechanical accelerometer with plasmonic MIM waveguide and structural direction-dependent optical signatures.

Scientific reports·2026
Same journal

Holographic leaky-wave antennas with independently controlled multiple counter-rotating vortex beams.

Scientific reports·2026
Same journal

Differential associations of longitudinal hearing and vision trajectories with dementia and mild cognitive impairment in older adults.

Scientific reports·2026
Same journal

Abdominal obesity and leisure-time sedentary behavior in relation to gastroesophageal reflux disease risk: a prospective cohort study from the UK Biobank.

Scientific reports·2026
Same journal

Effect of nitrogen-rich COF incorporation on the structure and separation performance of polyamide nanofiltration membranes.

Scientific reports·2026
Same journal

Withanolide A inhibits hIAPP aggregation: An In silico, biophysical, and drosophila-based In vivo validation.

Scientific reports·2026
See all related articles

This study introduces a hybrid medical image compression method using Discrete Wavelet Transform (DWT) and Cross-Attention Learning (CAL). The novel approach enhances compression efficiency while preserving diagnostic accuracy for telemedicine and healthcare storage.

Area of Science:

  • Medical Imaging
  • Data Compression
  • Artificial Intelligence

Background:

  • Efficient medical image compression is crucial for telemedicine and cloud storage.
  • Lossless methods offer limited compression, while lossy methods risk diagnostic accuracy.

Purpose of the Study:

  • To develop a novel hybrid compression framework for medical images.
  • To preserve clinically relevant details while reducing data size.

Main Methods:

  • Combined Discrete Wavelet Transform (DWT) with a deep Cross-Attention Learning (CAL) module.
  • Emphasized high-information regions using dynamic feature weighting.
  • Utilized a lightweight Variational Autoencoder (VAE) for feature refinement before entropy coding.

Main Results:

Keywords:
Cross-attention learningDeep learningImage reconstructionMedical image compressionTelemedicineWavelet transform

More Related Videos

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

3.3K

Related Experiment Videos

Last Updated: Jan 11, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729
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

3.3K
  • Achieved superior performance in PSNR, SSIM, and MSE compared to JPEG2000 and BPG.
  • Demonstrated effectiveness on benchmark datasets (LIDC-IDRI, LUNA16, MosMed).

Conclusions:

  • The proposed hybrid framework offers efficient medical image compression.
  • Potential for real-time transmission and storage without compromising diagnostic integrity.