Institute Affiliations

  • Member, Maternal & Child Health Research Institute (MCHRI)

Stanford Advisors

All Publications

  • Reconfigurable heterogeneous integration using stackable chips with embedded artificial intelligence NATURE ELECTRONICS Choi, C., Kim, H., Kang, J., Song, M., Yeon, H., Chang, C. S., Suh, J., Shin, J., Lu, K., Park, B., Kim, Y., Lee, H., Lee, D., Lee, J., Jang, I., Pang, S., Ryu, K., Bae, S., Nie, Y., Kum, H. S., Park, M., Lee, S., Kim, H., Wu, H., Lin, P., Kim, J. 2022
  • Accelerated 3D myelin water imaging using joint spatio-temporal reconstruction. Medical physics Lee, J., Yi, J., Kim, J., Ryu, K., Han, D., Kim, S., Lee, S., Kim, D. Y., Kim, D. 2022


    PURPOSE: To enable acceleration in 3D multi-echo gradient echo (mGRE) acquisition for myelin water imaging (MWI) by combining joint parallel imaging (JPI) and joint deep learning (JDL).METHODS: We implemented a multi-step reconstruction process using both advanced parallel imaging and deep learning network which can utilize joint spatio-temporal components between the multi-echo images to further accelerate 3D mGRE acquisition for MWI. In the first step, JPI was performed to estimate missing k-space lines. Next, JDL was implemented to reduce residual artifacts and produce high-fidelity reconstruction by using variable splitting optimization consisting of spatio-temporal denoiser block, data consistency block, and weighted average block. The proposed method was evaluated for MWI with 2D Cartesian uniform under-sampling for each echo, enabling scan times of up to approximately 2 minutes for 2 mm * 2 mm * 2 mm $2{\rm{mm}} \times 2{\rm{mm}} \times 2{\rm{mm}}$ 3D coverage.RESULTS: The proposed method showed acceptable MWI quality with improved quantitative values compared to both JPI methods and JDL method individually. The improved performance of the proposed method was demonstrated by the low normalized mean square error and high-frequency error norm values of the reconstruction with high similarity to the fully-sampled MWI.CONCLUSION: Joint spatio-temporal reconstruction approach by combining JPI and JDL can achieve high acceleration factors for 3D mGRE based MWI. This article is protected by copyright. All rights reserved.

    View details for DOI 10.1002/mp.15788

    View details for PubMedID 35678751

  • Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel. Magnetic resonance in medicine Ryu, K., Alkan, C., Vasanawala, S. S. 2022


    PURPOSE: Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures.METHODS: The proposed method constrains the output of the DL to comply to the linear neighborhood relationship calibrated in the auto-calibration lines. To demonstrate efficacy, we tested our refinement method on the DL reconstruction under a variety of conditions (i.e., dataset, unrolled neural networks, and under-sampling scheme). Specifically, the method was tested on three large-scale public datasets (knee and brain) from fastMRI's multi-coil track.RESULTS: The proposed scheme visually reduces the structural error in the k-space domain, enhance the homogeneity of the k-space intensity. Consequently, reconstructed image shows sharper images with enhanced details and textures. The proposed method is also successful in improving high-frequency image details (SSIM, GMSD) without sacrificing overall image error (PSNR).CONCLUSION: Our findings imply that refining DL output using the proposed method may generally improve DL reconstruction as tested with various large-scale dataset and networks.

    View details for DOI 10.1002/mrm.29261

    View details for PubMedID 35426470

  • Accelerated multi-contrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks. Medical physics Ryu, K., Lee, J., Nam, Y., Gho, S., Kim, H., Kim, D. 2021


    PURPOSE: Synthetic magnetic resonance imaging (MRI) requires the acquisition of multi-contrast images to estimate quantitative parameter maps, such as T1 , T2 , and proton density (PD). The study aims to develop a multi-contrast reconstruction method based on joint parallel imaging (JPI) and joint deep learning (JDL) to enable further acceleration of synthetic MRI.METHODS: The JPI and JDL methods are extended and combined to improve reconstruction for better-quality, synthesized images. JPI is performed as a first step to estimate the missing k-space lines, and JDL is then performed to correct and refine the previous estimate with a trained neural network. For the JDL architecture, the original variable splitting network (VS-Net) is modified and extended to form a joint variable splitting network (JVS-Net) to apply to multi-contrast reconstructions. The proposed method is designed and tested for multi-dynamic multi-echo (MDME) images with Cartesian uniform under-sampling using acceleration factors between 4 and 8.RESULTS: It is demonstrated that the nRMSE is lower and the structural similarity index (SSIM) values are higher with the proposed method compared to both the JPI and JDL methods individually. The method also demonstrates the potential to produce a set of synthesized contrast-weighted images that closely resemble those from the fully sampled acquisition without erroneous artifacts.CONCLUSION: Combining JPI and JDL enables the reconstruction of highly accelerated synthetic MRIs.

    View details for DOI 10.1002/mp.14848

    View details for PubMedID 33733464

  • Improving phase-based conductivity reconstruction by means of deep learning-based denoising of B 1 + phase data for 3T MRI. Magnetic resonance in medicine Jung, K. J., Mandija, S. n., Kim, J. H., Ryu, K. n., Jung, S. n., Cui, C. n., Kim, S. Y., Park, M. n., van den Berg, C. A., Kim, D. H. 2021


    To denoise B 1 + phase using a deep learning method for phase-based in vivo electrical conductivity reconstruction in a 3T MR system.For B 1 + phase deep-learning denoising, a convolutional neural network (U-net) was chosen. Training was performed on data sets from 10 healthy volunteers. Input data were the real and imaginary components of single averaged spin-echo data (SNR = 45), which was used to approximate the B 1 + phase. For label data, multiple signal-averaged spin-echo data (SNR = 128) were used. Testing was performed on in silico and in vivo data. Reconstructed conductivity maps were derived using phase-based conductivity reconstructions. Additionally, we investigated the usability of the network to various SNR levels, imaging contrasts, and anatomical sites (ie, T1 , T2 , and proton density-weighted brain images and proton density-weighted breast images. In addition, conductivity reconstructions from deep learning-based denoised data were compared with conventional image filters, which were used for data denoising in electrical properties tomography (ie, the Gaussian filtering and the Savitzky-Golay filtering).The proposed deep learning-based denoising approach showed improvement for B 1 + phase for both in silico and in vivo experiments with reduced quantitative error measures compared with other methods. Subsequently, this resulted in an improvement of reconstructed conductivity maps from the denoised B 1 + phase with deep learning.The results suggest that the proposed approach can be used as an alternative preprocessing method to denoise B 1 + maps for phase-based conductivity reconstruction without relying on image filters or signal averaging.

    View details for DOI 10.1002/mrm.28826

    View details for PubMedID 33949721

  • K-space refinement in deep learning MR reconstruction via regularizing scan specific SPIRiT-based self consistency Ryu, K., Alkan, C., Choi, C., Jang, I., Vasanawala, S., IEEE Comp Soc IEEE COMPUTER SOC. 2021: 3991-4000