🛰️ Daily AI Frontier
‹ back to 2026-07-22

SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction

Research Medical/Healthcare AI

Ranking

Overall 78
Content 80
Popularity 73

Observed public metrics from 1 member.

Merged summary

TL;DR - SHFormer combines dynamic spectral-filtering CNNs with a high-pass kernel generation transformer to preserve fine details in accelerated MRI reconstruction. It improves reconstruction and generalization across heterogeneous, previously unseen MRI domains.

  • Targets attention models’ tendency to favor low-frequency information and produce overly smooth reconstructions.
  • Learns mode-specific transferable features while emphasizing context-aware high-frequency details.
  • Evaluated across supervised, self-supervised, diffusion-based, closed-set, and open-set settings.
  • Reports best unseen-domain gains of approximately 1 dB PSNR and 0.01 SSIM.

Sources (1)

SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction

arXiv cs.CV Sriprabha Ramanarayanan, Rahul G. S., Mohammad Al Fahim, Keerthi Ram, Ramesh Venkatesan, Mohanasankar Sivaprakasam 2026-07-22 arXiv:2607.20159 doi:10.1016/j.neunet.2025.107334
Public signals OpenAlex citations 5 · Semantic Scholar citations 6 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · Citations 5 Publisher · N/A Semantic Scholar · Citations 6 · Influential citations 0 X · N/A Fetched 2026-08-21 14:38:36.288664 UTC

TL;DR - SHFormer combines dynamic spectral-filtering CNNs with a high-pass kernel generation transformer to preserve fine details in accelerated MRI reconstruction. It improves reconstruction and generalization across heterogeneous, previously unseen MRI domains.

  • Targets attention models’ tendency to favor low-frequency information and produce overly smooth reconstructions.
  • Learns mode-specific transferable features while emphasizing context-aware high-frequency details.
  • Evaluated across supervised, self-supervised, diffusion-based, closed-set, and open-set settings.
  • Reports best unseen-domain gains of approximately 1 dB PSNR and 0.01 SSIM.
item →