Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 10, 2025Japanese Journal of RadiologyOpen Access

Super-resolution deep learning reconstruction improves brain MRI quality and detection of metastases

View Full Paper
Ask AI
Bookmark
Share

Authors

YAYusuke AsariKYKoichiro YasakaJKJun Kanzawa

Discussion

Loading...

Member takes

Implication

Retrospective study finds super-resolution techniques improve image quality and detect metastases in brain MRI, suggesting enhanced patient evaluation.

Key Points

  • This study aims to evaluate the effectiveness of super-resolution deep learning reconstruction compared to conventional methods in detecting brain metastases.
  • Retrospective analysis of 47 patients undergoing postcontrast 3D whole-brain T1-weighted MRI.
  • Comparison of image reconstruction methods: super-resolution deep learning reconstruction (SR-DLR) and conventional deep learning reconstruction (DLR).
  • Evaluation of image quality and lesion detection by three independent readers using subjective and objective metrics.
  • 117 brain metastases were identified in the patient cohort.
  • SR-DLR showed significantly improved detection performance compared to DLR (mean figure of merit: 0.842 vs. 0.797).
  • Subjective ratings favored SR-DLR for visibility, sharpness, noise levels, and overall image quality in most evaluations.

Cite This Study

Asari et al. (2025) studied this question.

synapsesocial.com/papers/69401d542d562116f28f89e3https://doi.org/10.1007/s11604-025-01921-3
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. 1Super-resolution deep learning reconstruction improves brain MRI quality and detection of metastases2025
  2. 2Super-Resolution Deep Learning Reconstruction for 3-Dimensional T1-Weighted Gradient-Echo Imaging in Contrast-Enhanced Liver MRI: Comparison With Conventional and Standard Deep Learning Reconstructions2026
  3. 3Super-resolution deep learning reconstruction enhances visualization of cerebral aneurysms on magnetic resonance angiography2026
  4. 4Multidisciplinary, Clinical Assessment of Accelerated Deep-Learning MRI Protocols at 1.5 T and 3 T After Intracranial Tumor Surgery and Their Influence on Residual Tumor Perception2025 · 4 citations
  5. 5Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction2024 · 12 citations