Dongchan Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dongchan Kim has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- HyunWook Park
School of Electrical Engineering KAIST Daejeon
5 shared publications - Byungjai Kim
Department of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea
2 shared publications Hyunseok Seo
Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Guseong-dong, Yuseong-gu, Daejeon, South Korea
2 shared publicationsKinam Kwon
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
2 shared publications- Yeji Han
Department of Biomedical Engineering, College of Health Sciences, Gachon University, Hambakmoero 191, Yeonsu-gu, Incheon, Republic of Korea
2 shared publications - Chang-Hyun Oh
Department of Electronics and Information Engineering, Korea University, Sejong 30019, Republic of Korea
1 shared publication
Latest Publications
- 12 August 2019
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 83 (1) , 124-138
Unsupervised learning of a deep neural network for metal artifact correction using dual‐polarity readout gradients
Purpose: A new unsupervised learning method was developed to correct metal artifacts in MRI using 2 distorted images obtained with dual‐polarity readout gradients.Methods: An unsupervised learning method is proposed for a deep neural network architecture consisting of a deep neural network and an MR image generation module. The architecture is trained as an end‐to‐end process without the use of distortion‐free images or off‐resonance frequency maps. The deep neural network estimates frequency‐shift maps between 2 distorted images that are obtained using dual‐polarity readout gradients. From the estimated frequency‐shift maps and 2 distorted input images, distortion‐corrected images are obtained with the MR image generation module. Experiments using synthetic data and actual MR data were performed to compare images corrected by several metal‐artifact‐correction methods.Results: The proposed method resolved the ripple and pile‐up artifacts in the reconstructed images from synthetic data and actual MR data. The results from the proposed method were comparable to those from supervised‐learning methods and superior to the compared model‐based method. The proposed unsupervised learning method enabled the network to be trained without labels and to be more robust than supervised learning methods, for which overfitting problems can arise when using small training data sets.Conclusion: Metal artifacts in the MR image were drastically corrected by the proposed unsupervised learning method. Two distorted images obtained with dual‐polarity readout gradients are used as the input of the deep neural network. The proposed method can train networks without labels and does not overfit the network, even with small training data sets.
- 12 August 2019
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 83 (1) , 124-138
Unsupervised learning of a deep neural network for metal artifact correction using dual‐polarity readout gradients
Purpose: A new unsupervised learning method was developed to correct metal artifacts in MRI using 2 distorted images obtained with dual‐polarity readout gradients.Methods: An unsupervised learning method is proposed for a deep neural network architecture consisting of a deep neural network and an MR image generation module. The architecture is trained as an end‐to‐end process without the use of distortion‐free images or off‐resonance frequency maps. The deep neural network estimates frequency‐shift maps between 2 distorted images that are obtained using dual‐polarity readout gradients. From the estimated frequency‐shift maps and 2 distorted input images, distortion‐corrected images are obtained with the MR image generation module. Experiments using synthetic data and actual MR data were performed to compare images corrected by several metal‐artifact‐correction methods.Results: The proposed method resolved the ripple and pile‐up artifacts in the reconstructed images from synthetic data and actual MR data. The results from the proposed method were comparable to those from supervised‐learning methods and superior to the compared model‐based method. The proposed unsupervised learning method enabled the network to be trained without labels and to be more robust than supervised learning methods, for which overfitting problems can arise when using small training data sets.Conclusion: Metal artifacts in the MR image were drastically corrected by the proposed unsupervised learning method. Two distorted images obtained with dual‐polarity readout gradients are used as the input of the deep neural network. The proposed method can train networks without labels and does not overfit the network, even with small training data sets.
- 10 April 2019
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 29 (4) , 476-482
Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database
Accurate extraction of brain tissues from magnetic resonance (MR) images is important in neuroradiology. However, brain extraction is more difficult for pediatric brains than for adult brains due to several factors including smaller brain sizes and lower tissue contrasts. In this work, we propose a brain extraction technique that utilizes dual frame (DF) 3D U‐net deep learning architecture and the human connectome project (HCP) database for multislice 2D pediatric T2‐weighted MR images with diseases. To improve segmentation accuracy in small pediatric brains with detailed boundary regions, DF 3D U‐net architecture was used. We pretrained networks with the HCP database to compensate for the limited amount of MR images and manual segmentation masks of pediatric patients. For quantitative analysis, we compared the brain extraction results of brain extraction tool, DF, and conventional 3D U‐net using the dice similarity coefficient (DSC), intersection of union (IoU), and boundary F1 (BF) scores; each deep learning architecture was evaluated with and without pretraining using the HCP. This study included 10 patients with diseases and all images were acquired using a PROPELLER MR sequence. Pretraining using the HCP database enhanced segmentation performance of the network, and the skip connections in the DF 3D U‐net could enhance the contour similarity of segmentation results. Experimental results showed that the proposed method increased the DSC, IoU, and BF scores by 0.8%, 1.6%, and 1.5%, respectively, compared with those of the conventional 3D U‐net without pretraining.
- 10 April 2019
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 29 (4) , 476-482
Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database
Accurate extraction of brain tissues from magnetic resonance (MR) images is important in neuroradiology. However, brain extraction is more difficult for pediatric brains than for adult brains due to several factors including smaller brain sizes and lower tissue contrasts. In this work, we propose a brain extraction technique that utilizes dual frame (DF) 3D U‐net deep learning architecture and the human connectome project (HCP) database for multislice 2D pediatric T2‐weighted MR images with diseases. To improve segmentation accuracy in small pediatric brains with detailed boundary regions, DF 3D U‐net architecture was used. We pretrained networks with the HCP database to compensate for the limited amount of MR images and manual segmentation masks of pediatric patients. For quantitative analysis, we compared the brain extraction results of brain extraction tool, DF, and conventional 3D U‐net using the dice similarity coefficient (DSC), intersection of union (IoU), and boundary F1 (BF) scores; each deep learning architecture was evaluated with and without pretraining using the HCP. This study included 10 patients with diseases and all images were acquired using a PROPELLER MR sequence. Pretraining using the HCP database enhanced segmentation performance of the network, and the skip connections in the DF 3D U‐net could enhance the contour similarity of segmentation results. Experimental results showed that the proposed method increased the DSC, IoU, and BF scores by 0.8%, 1.6%, and 1.5%, respectively, compared with those of the conventional 3D U‐net without pretraining.
- 10 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 29 (10) , 2888-2898
A New No-Reference Method for Judder Artifact Assessment
This paper proposes a new metric to measure judder artifacts of video sequences. The judder artifacts appear as non-smooth motions in hold-type displays when the frame rate is low and object motion is fast. To analyze the judder artifacts in video sequences, the proposed judder metric is defined by analyzing the effects and cross-relations of judder features in the video sequences. The judder features include spatial features of image gradients and temporal features of motion vectors and the frame rate. In addition, sensitivity of the human visual system (HVS) is considered to determine the perceptual judder artifacts because it has special characteristics of sensitivity to image brightness and contrast. Therefore, a sensitivity map of the HVS is used to mask the judder artifacts. Then, the degree of perceptual judder artifacts is estimated using the judder features and a regression model. The experimental results demonstrate that the proposed judder metric is highly correlated with the subjective assessment results.
- 10 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 29 (10) , 2888-2898
A New No-Reference Method for Judder Artifact Assessment
This paper proposes a new metric to measure judder artifacts of video sequences. The judder artifacts appear as non-smooth motions in hold-type displays when the frame rate is low and object motion is fast. To analyze the judder artifacts in video sequences, the proposed judder metric is defined by analyzing the effects and cross-relations of judder features in the video sequences. The judder features include spatial features of image gradients and temporal features of motion vectors and the frame rate. In addition, sensitivity of the human visual system (HVS) is considered to determine the perceptual judder artifacts because it has special characteristics of sensitivity to image brightness and contrast. Therefore, a sensitivity map of the HVS is used to mask the judder artifacts. Then, the degree of perceptual judder artifacts is estimated using the judder features and a regression model. The experimental results demonstrate that the proposed judder metric is highly correlated with the subjective assessment results.
- 12 September 2018
- Published by Springer Nature
- p. 12-20
ETER-net: End to End MR Image Reconstruction Using Recurrent Neural Network
- 12 September 2018
- Published by Springer Nature
- p. 12-20
ETER-net: End to End MR Image Reconstruction Using Recurrent Neural Network
- 20 December 2017
- Published by Wiley in NMR in Biomedicine
- Vol. 31 (3)
Retrospective motion gating in cardiac MRI using a simultaneously acquired navigator
A simultaneous acquisition technique of image and navigator signals (simultaneously acquired navigator, SIMNAV) is proposed for cardiac magnetic resonance imaging (CMRI) in Cartesian coordinates. To simultaneously acquire both image and navigator signals, a conventional balanced steady‐state free precession (bSSFP) pulse sequence is modified by adding a radiofrequency (RF) pulse, which excites a supplementary slice for the navigator signal. Alternating phases of the RF pulses make it easy to separate the simultaneously acquired magnetic resonance data into image and navigator signals. The navigator signals of the proposed SIMNAV were compared with those of current gating devices and self‐gating techniques for seven healthy subjects. In vivo experiments demonstrated that SIMNAV could provide cardiac cine images with sufficient image quality, similar to those from electrocardiogram (ECG) gating with breath‐hold. SIMNAV can be used to acquire a cardiac cine image without requiring an ECG device and breath‐hold, whilst maintaining feasible imaging time efficiency.
- 20 December 2017
- Published by Wiley in NMR in Biomedicine
- Vol. 31 (3)
Retrospective motion gating in cardiac MRI using a simultaneously acquired navigator
A simultaneous acquisition technique of image and navigator signals (simultaneously acquired navigator, SIMNAV) is proposed for cardiac magnetic resonance imaging (CMRI) in Cartesian coordinates. To simultaneously acquire both image and navigator signals, a conventional balanced steady‐state free precession (bSSFP) pulse sequence is modified by adding a radiofrequency (RF) pulse, which excites a supplementary slice for the navigator signal. Alternating phases of the RF pulses make it easy to separate the simultaneously acquired magnetic resonance data into image and navigator signals. The navigator signals of the proposed SIMNAV were compared with those of current gating devices and self‐gating techniques for seven healthy subjects. In vivo experiments demonstrated that SIMNAV could provide cardiac cine images with sufficient image quality, similar to those from electrocardiogram (ECG) gating with breath‐hold. SIMNAV can be used to acquire a cardiac cine image without requiring an ECG device and breath‐hold, whilst maintaining feasible imaging time efficiency.
- 5 June 2017
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 79 (2) , 779-788
Non‐contrast‐enhanced peripheral MR angiography using velocity‐selective excitation
Purpose: To develop a new non‐contrast‐enhanced peripheral MR angiography that provides a high contrast angiogram without using electrocardiography triggering and saturation radiofrequency pulses.Methods: A velocity‐selective excitation technique is used in conjunction with the golden‐angle radial sampling scheme. The signal amplitude varies according to the velocity of the flow by the velocity‐selective excitation technique. Because the arterial blood velocity varies depending on the cardiac phase, the acquired data can be classified into systolic and diastolic phase based on the signal amplitude of the artery. Two images are then reconstructed from the systolic and diastolic phase data, respectively, and an image reflecting the differences between the two images is obtained to eliminate background and vein signals. The performance of the proposed method was compared with the quiescent‐interval single shot (QISS) in eight healthy subjects and an elderly subject.Results: The proposed method generated fewer residual venous and background signals than the QISS. Furthermore, the maximum intensity projection images, the relative contrast, and the apparent contrast‐to‐noise ratio results showed that the proposed method produced a better contrast than the QISS.Conclusions: The proposed non‐contrast‐enhanced peripheral MR angiography technique can provide a high contrast angiogram without the use of electrocardiography triggering and saturation radiofrequency pulses. Magn Reson Med 79:779–788, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
- 5 June 2017
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 79 (2) , 779-788
Non‐contrast‐enhanced peripheral MR angiography using velocity‐selective excitation
Purpose: To develop a new non‐contrast‐enhanced peripheral MR angiography that provides a high contrast angiogram without using electrocardiography triggering and saturation radiofrequency pulses.Methods: A velocity‐selective excitation technique is used in conjunction with the golden‐angle radial sampling scheme. The signal amplitude varies according to the velocity of the flow by the velocity‐selective excitation technique. Because the arterial blood velocity varies depending on the cardiac phase, the acquired data can be classified into systolic and diastolic phase based on the signal amplitude of the artery. Two images are then reconstructed from the systolic and diastolic phase data, respectively, and an image reflecting the differences between the two images is obtained to eliminate background and vein signals. The performance of the proposed method was compared with the quiescent‐interval single shot (QISS) in eight healthy subjects and an elderly subject.Results: The proposed method generated fewer residual venous and background signals than the QISS. Furthermore, the maximum intensity projection images, the relative contrast, and the apparent contrast‐to‐noise ratio results showed that the proposed method produced a better contrast than the QISS.Conclusions: The proposed non‐contrast‐enhanced peripheral MR angiography technique can provide a high contrast angiogram without the use of electrocardiography triggering and saturation radiofrequency pulses. Magn Reson Med 79:779–788, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
- 15 April 2013
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 58 (9) , 2969-2988
An iterative reconstruction method of complex images using expectation maximization for radial parallel MRI
In MRI (magnetic resonance imaging), signal sampling along a radial k-space trajectory is preferred in certain applications due to its distinct advantages such as robustness to motion, and the radial sampling can be beneficial for reconstruction algorithms such as parallel MRI (pMRI) due to the incoherency. For radial MRI, the image is usually reconstructed from projection data using analytic methods such as filtered back-projection or Fourier reconstruction after gridding. However, the quality of the reconstructed image from these analytic methods can be degraded when the number of acquired projection views is insufficient. In this paper, we propose a novel reconstruction method based on the expectation maximization (EM) method, where the EM algorithm is remodeled for MRI so that complex images can be reconstructed. Then, to optimize the proposed method for radial pMRI, a reconstruction method that uses coil sensitivity information of multichannel RF coils is formulated. Experiment results from synthetic and in vivo data show that the proposed method introduces better reconstructed images than the analytic methods, even from highly subsampled data, and provides monotonic convergence properties compared to the conjugate gradient based reconstruction method.
- 15 April 2013
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 58 (9) , 2969-2988
An iterative reconstruction method of complex images using expectation maximization for radial parallel MRI
In MRI (magnetic resonance imaging), signal sampling along a radial k-space trajectory is preferred in certain applications due to its distinct advantages such as robustness to motion, and the radial sampling can be beneficial for reconstruction algorithms such as parallel MRI (pMRI) due to the incoherency. For radial MRI, the image is usually reconstructed from projection data using analytic methods such as filtered back-projection or Fourier reconstruction after gridding. However, the quality of the reconstructed image from these analytic methods can be degraded when the number of acquired projection views is insufficient. In this paper, we propose a novel reconstruction method based on the expectation maximization (EM) method, where the EM algorithm is remodeled for MRI so that complex images can be reconstructed. Then, to optimize the proposed method for radial pMRI, a reconstruction method that uses coil sensitivity information of multichannel RF coils is formulated. Experiment results from synthetic and in vivo data show that the proposed method introduces better reconstructed images than the analytic methods, even from highly subsampled data, and provides monotonic convergence properties compared to the conjugate gradient based reconstruction method.