Deep Learning-Based Denoising for High-Resolution Carotid Vessel Wall MRI Using Standard Neurovascular Coils.

Journal: Magnetic resonance in medicine
Published Date: Dec 19, 2025

Abstract

PURPOSE: To develop a deep learning (DL) denoising method to enhance high-resolution carotid vessel wall MRI quality acquired using a standard head-and-neck clinical coil. METHODS: Fifty-five scans were performed as part of an ongoing multicenter study. Routine carotid VWI protocol including 2D T1- and T2-weighted TSE, 3D TOF-MRA, and MPRAGE was performed using simultaneous acquisition from a standard 20-channel head-and-neck coil and a high-sensitivity Neck-Shape-Specific (NSS) surface coil. Paired retrospective reconstructions with and without NSS coil elements served as the reference and input, respectively. A supervised DL model employing a residual UNet architecture was optimized and trained to map low-SNR inputs to high-SNR references, benchmarked against conventional denoising algorithms using quantitative and qualitative metrics. RESULTS: The DL denoiser substantially reduced noise while preserving vessel-wall structures across contrast-weighted sequences. It achieved PSNR > 31 dB and structural similarity index (SSIM) > 0.93 versus reference slices. In segmented vessel-wall and lumen regions of interest (ROIs), the DL approach achieved significantly higher SNR and CNR values than input images (p < 0.05), closely approaching the reference. Furthermore, inner-wall edge sharpness was maintained (Average ERD 7.50-8.51 mm with DL vs. 7.15-8.28 mm with references), supporting confident downstream plaques assessment. Radiologists' Likert ratings corroborated these image-quality improvements. CONCLUSION: A DL-based method was developed to improve high-resolution, multi-contrast carotid vessel wall MRI acquired using low-SNR standard head-and-neck coils. The resulting image quality was comparable to that obtained with specialized neck surface coils, potentially enabling broader access to advanced carotid imaging without the need for additional hardware.

Authors

  • Lisha Zeng
    Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.
  • Yin-Chen Hsu
    Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, 6500 Wilshire Blvd, Los Angeles, CA 90048.
  • Lixia Wang
    Department of Radiology, Chaoyang Hospital, Beijing, China.
  • Meng Lu
    Department of Electrical and Computer Engineering, Iowa State University, Ames, IA 50011, United States; Department of Mechanical Engineering, Iowa State University, Ames, IA 500110, United States. Electronic address: [email protected].
  • Mary Keushkerian
    Department of Cardiology, Radiology, and Bioengineering, UCLA, Los Angeles, California, USA.
  • Kim-Lien Nguyen
    Department of Medicine, Division of Cardiology, David Geffen School of Medicine, University of California, Los Angeles, California, USA.
  • Kevin J Johnson
    Department of Medical Imaging, University of Arizona, Tucson, Arizona, USA.
  • Maria I Altbach
    Department of Radiology, The University of Arizona, Tucson, Arizona, USA.
  • H Douglas Morris
    Department of Radiology and Bioengineering, Uniformed Services University for Health Science, 4301 Jones Bridge Rd, Bethesda, MD 20814, USA.
  • J Kevin DeMarco
    Walter Reed National Military Medical Center, Bethesda, Maryland, USA.
  • Vibhas Deshpande
    Siemens Medical Solutions USA, Austin, Texas, USA.
  • Dimitrios Mitsouras
    From the Applied Imaging Science Laboratory, Department of Radiology, Brigham and Women's Hospital, 75 Francis St, Boston, MA 02115 (T.C., A.A.G., K.K.K., F.J.R., D.M.); Harvard T.H. Chan School of Public Health, Boston, Mass (S.Y.); and Department of Radiology, Brigham and Women's Hospital, Boston, Mass (T.K., B.R.).
  • David Saloner
    Department of Radiology and Biomedical Imaging, UCSF, San Francisco, California, USA.
  • J Scott McNally
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.
  • Seong-Eun Kim
    Department of Mechanical Engineering, Pohang University of Science and Technology, Pohang (POSTECH), 77, Cheongam-ro, Nam-gu, Pohang, Gyeongbuk 37673, South Korea. [email protected].
  • John A Roberts
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.
  • J Rock Hadley
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.
  • Dennis L Parker
    Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah, USA.
  • Gerald S Treiman
    VA Salt Lake City, Salt Lake City, Utah, USA.
  • Debiao Li
  • Yibin Xie
    Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals