Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 18, 2026Journal of Imaging Informatics in MedicineOpen Access

Deep Generative Translation of Standard Images into Virtual High-Energy Images for Facilitating Dual-Energy Chest Radiography

View Full Paper
Ask AI
Bookmark
Share

Authors

YUYasuyuki UedaRSRiko ShimazakiMSMasashi Seki

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates the generation of virtual high-energy images from standard images, suggesting enhanced diagnostic capabilities.

Key Points

  • This research aims to develop a model for transforming standard chest radiographs into virtual high-energy images for enhanced visualization.
  • Developed a U-Net-based model for translating standard images to high-energy images using the pix2pix framework.
  • Employed a dataset of 600 triplet chest radiographs (STD, HE, LE) and used a sixfold cross-validation approach over 2000 epochs.
  • Evaluated image quality metrics (PSNR, SSIM, DISTS) to assess the generated virtual images.
  • The STD2HE model achieved a PSNR of 34.5, SSIM of 0.979, and DISTS of 0.0257 for high-energy images compared to groundtruth HE images.
  • The virtual LE images exhibited a PSNR of 35.1, SSIM of 0.963, and DISTS of 0.0455 when compared to groundtruth LE images.
  • Virtual DES images showed a Fréchet inception distance of 67.6 and 73.6 for BS and BE images, indicating high structural fidelity.

Cite This Study

Ueda et al. (2026) studied this question.

synapsesocial.com/papers/6a5b193518557b26c203ac29https://doi.org/10.1007/s10278-026-02105-9
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Synthetic Low-Energy Monochromatic Image Generation in Single-Energy Computed Tomography System Using a Transformer-Based Deep Learning Model2024 · 2 citations
  2. 2Contrast-enhanced dual-energy CT synthesis from single energy CT using diffusion model2024
  3. 3Deep learning-based dual-energy subtraction synthesis from single-energy kV x-ray fluoroscopy for markerless tumor tracking2025
  4. 4Dual-energy CT-based virtual monoenergetic imaging via unsupervised learning2024
  5. 5Conversion of single-energy CT to parametric maps of dual-energy CT using convolutional neural network2024 · 6 citations