Improving the brain image resolution of generalized q-sampling MRI revealed by a three-dimensional CNN-based method

Chun-Yuan Shin; Yi-Ping Chao; Li-Wei Kuo; Yi-Peng Eve Chang; Jun-Cheng Weng

doi:10.3389/fninf.2023.956600

Improving the brain image resolution of generalized q-sampling MRI revealed by a three-dimensional CNN-based method

Front Neuroinform. 2023 Feb 16:17:956600. doi: 10.3389/fninf.2023.956600. eCollection 2023.

Authors

Chun-Yuan Shin¹, Yi-Ping Chao^{2

3}, Li-Wei Kuo^{4

5}, Yi-Peng Eve Chang⁶, Jun-Cheng Weng^{1

7

8

9}

Affiliations

¹ Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan.
² Department of Computer Science and Information Engineering, Chang Gung University, Taoyuan, Taiwan.
³ Department of Biomedical Engineering, Chang Gung University, Taoyuan, Taiwan.
⁴ Institute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Miaoli, Taiwan.
⁵ Institute of Medical Device and Imaging, National Taiwan University College of Medicine, Taipei City, Taiwan.
⁶ Department of Counseling and Clinical Psychology, Columbia University, New York City, NY, United States.
⁷ Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.
⁸ Department of Artificial Intelligence, Chang Gung University, Taoyuan, Taiwan.
⁹ Department of Psychiatry, Chang Gung Memorial Hospital, Chiayi, Taiwan.

Abstract

Background: Understanding neural connections facilitates the neuroscience and cognitive behavioral research. There are many nerve fiber intersections in the brain that need to be observed, and the size is between 30 and 50 nanometers. Improving image resolution has become an important issue for mapping the neural connections non-invasively. Generalized q-sampling imaging (GQI) was used to reveal the fiber geometry of straight and crossing. In this work, we attempted to achieve super-resolution with a deep learning method on diffusion weighted imaging (DWI).

Materials and methods: A three-dimensional super-resolution convolutional neural network (3D SRCNN) was utilized to achieve super-resolution on DWI. Then, generalized fractional anisotropy (GFA), normalized quantitative anisotropy (NQA), and the isotropic value of the orientation distribution function (ISO) mapping were reconstructed using GQI with super-resolution DWI. We also reconstructed the orientation distribution function (ODF) of brain fibers using GQI.

Results: With the proposed super-resolution method, the reconstructed DWI was closer to the target image than the interpolation method. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were also significantly improved. The diffusion index mapping reconstructed by GQI also had higher performance. The ventricles and white matter regions were much clearer.

Conclusion: This super-resolution method can assist in postprocessing low-resolution images. With SRCNN, high-resolution images can be effectively and accurately generated. The method can clearly reconstruct the intersection structure in the brain connectome and has the potential to accurately describe the fiber geometry on a subvoxel scale.

Keywords: diffusion MRI; generalized q-sampling imaging (GQI); peak signal-to-noise ratio (PSNR); structural similarity index measure (SSIM); super-resolution convolutional neural network (SRCNN).

Grants and funding

This study was supported by the research programs NSTC111-2221-E-182-021, NSTC110-2221-E-182-009-MY2, NMRPD1M0971, BMRPC78, and CMRPD1H0421 sponsored by the National Science and Technology Council, Taipei City, Taiwan and Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan.