PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
April 13, 2026IEEE Journal of Biomedical and Health Informatics

DF-DiffVSR: Deformable Field-Driven Diffusion Model for Inter-Slice Continuity Enhancement in Medical Volume Super-Resolution

View Full Paper
Ask AI
Bookmark
Share

Authors

CWChen WangMLMing LiuQLQinghao Liu

Discussion

Loading...

Member takes

Overview

A novel model enhances inter-slice continuity in medical imaging, implying improved diagnosis accuracy.

Key Points

  • Enhance inter-slice continuity in medical volumetric imaging through a novel super-resolution model.
  • Introduced DF-DiffVSR, a deformable field-driven diffusion model.
  • Integrated optical flow principles with diffusion models via a Deformable Field Extraction module.
  • Developed a Multiscale Large Kernel Convolution module for expanded receptive fields.
  • Achieved state-of-the-art performance in medical super-resolution.
  • Surpassed competing methods by 0.732 dB and 0.214 dB in PSNR on RPLHR-CT and IXI-T2 datasets, respectively.
  • Demonstrated improved preservation of inter-slice continuity and detail recovery.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/69dc88303afacbeac03ea14chttps://doi.org/10.1109/jbhi.2026.3682766
View Full Paper
Ask AI
Bookmark
Share