EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HACR-Net: An Efficient hybrid attention network for MRI image super-resolution

Abdulhamid Muhammad, Amir Hajian, Titipat Achakulvisut, Supavadee Aramvith iD

PLOS One · 08.04.2026 · 21 (4) · e0345637

DOI: 10.1371/journal.pone.0345637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 08.04.2026. Verfasst von Abdulhamid Muhammad und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chulalongkorn University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution Magnetic Resonance Imaging (MRI) plays an important role in clinical diagnosis and pathological assessment, due to its non-invasive nature and lack of ionizing radiation. However, the acquisition of high-resolution MRI is often constrained by hardware limitations and a prolonged scanning duration. To address these limitations, super-resolution (SR) techniques have been introduced to reconstruct high-resolution images from low-resolution inputs. However, despite these advances, existing methods often struggle to effectively extract shallow features, model complex contextual dependencies, and preserve fine anatomical details. To address these limitations, we propose a Hybrid Attention and Channel Retention Network (HACR-Net) for MRI image SR. HACR-Net incorporates a Hybrid Attention Module (HAM) to mitigate information loss during shallow feature extraction by jointly leveraging channel and spatial attention, enhancing informative features, and preserving spatially significant regions. A Multiscale Feature Aggregation Block (MFAB) is incorporated to capture global structural details, local texture, and high-frequency details. Complementing MFAB, the Channel Retention Attention Block (CRAB) enhances the recovery of fine contextual detail through a bottleneck design crafted to maintain a wider channel width and reduce information loss during feature compression. Extensive experiments on two benchmark datasets, IXI and BraTS2018, demonstrate that HACR-Net achieves high-performance reconstruction with only 1.67M parameters and 81.3G FLOPs, offering significant reductions in model size and computational cost compared to existing methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImage Processing, Computer-AssistedHumansAlgorithmsBrain

Autor:innen und Institutionen

  • Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand.
  • Department of Biomedical Engineering, Faculty of Engineering, Mahidol University, Salaya, Nakhon Pathom, Thailand.
  • Multimedia Data Analytics and Processing Research Unit, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand.

ORCID-Profile: Supavadee Aramvith

Förderung

  • Chulalongkorn University

Zitieren

APA

Muhammad, A., Hajian, A., Achakulvisut, T., & Aramvith, S. (2026). HACR-Net: An Efficient hybrid attention network for MRI image super-resolution. PLOS One, 21(4), e0345637. https://doi.org/10.1371/journal.pone.0345637

Vancouver

Muhammad A, Hajian A, Achakulvisut T, Aramvith S. HACR-Net: An Efficient hybrid attention network for MRI image super-resolution. PLOS One. 2026;21(4):e0345637. doi:10.1371/journal.pone.0345637

BibTeX
@article{Muhammad2026,
  author = {Muhammad, Abdulhamid and Hajian, Amir and Achakulvisut, Titipat and Aramvith, Supavadee},
  title = {HACR-Net: An Efficient hybrid attention network for MRI image super-resolution},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0345637},
  doi = {10.1371/journal.pone.0345637}
}
Kostenlos starten →