Jonghyon Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jonghyon Yi has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Ji Hye Min
Department of Radiology and Center for Imaging Science, Samsung Medical Center Sungkyunkwan University School of Medicine Seoul South Korea
2 shared publications - Byung Eun Ahn
AITRICS Corp, Seoul, Republic of Korea
1 shared publication - Dong Hyun Sinn
Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
1 shared publication - Dong Ik Cha
Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
1 shared publication Dongil Choi
Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 135-710, Republic of Korea
1 shared publication- Dongwoo Kim
Affiliation Bot Fit T/F, New Business Team, Samsung Electronics, Suwon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 1 October 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (4) , 565-574
Deep learning-based automated quantification of the hepatorenal index for evaluation of fatty liver by ultrasonography
Purpose: The aim of this study was to develop and validate a fully-automatic quantification of the hepatorenal index (HRI) calculated by a deep convolutional neural network (DCNN) comparable to the interpretations of radiologists experienced in ultrasound (US) imaging.Methods: In this retrospective analysis, DCNN-based organ segmentation with Gaussian mixture modeling for automated quantification of the HRI was developed using abdominal US images from a previous study. For validation, 294 patients who underwent abdominal US examination before living-donor liver transplantation were selected. Interobserver agreement for the measured brightness of the liver and kidney and the calculated HRI were analyzed between two board-certified radiologists and DCNN using intraclass correlation coefficients (ICCs).Results: Most patients had normal (n=95) or mild (n=198) fatty liver. The ICCs of hepatic and renal brightness measurements and the calculated HRI between the two radiologists were 0.892 (95% confidence interval [CI], 0.866 to 0.913), 0.898 (95% CI, 0.873 to 0.918), and 0.681 (95% CI, 0.615 to 0.738) for the first session and 0.920 (95% CI, 0.901 to 0.936), 0.874 (95% CI, 0.844 to 0.898), and 0.579 (95% CI, 0.497 to 0.650) for the second session, respectively; the results ranged from moderate to excellent agreement. Using the same task, the ICCs of the hepatic and renal measurements and the calculated HRI between the average values of the two radiologists and DCNN were 0.919 (95% CI, 0.899 to 0.935), 0.916 (95% CI, 0.895 to 0.932), and 0.734 (95% CI, 0.676 to 0.782), respectively, showing high to excellent agreement.Conclusion: Automated quantification of HRI using DCNN can yield HRI measurements similar to those obtained by experienced radiologists in patients with normal or mild fatty liver.
- 1 October 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (4) , 565-574
Open AccessDeep learning-based automated quantification of the hepatorenal index for evaluation of fatty liver by ultrasonography
Purpose: The aim of this study was to develop and validate a fully-automatic quantification of the hepatorenal index (HRI) calculated by a deep convolutional neural network (DCNN) comparable to the interpretations of radiologists experienced in ultrasound (US) imaging.Methods: In this retrospective analysis, DCNN-based organ segmentation with Gaussian mixture modeling for automated quantification of the HRI was developed using abdominal US images from a previous study. For validation, 294 patients who underwent abdominal US examination before living-donor liver transplantation were selected. Interobserver agreement for the measured brightness of the liver and kidney and the calculated HRI were analyzed between two board-certified radiologists and DCNN using intraclass correlation coefficients (ICCs).Results: Most patients had normal (n=95) or mild (n=198) fatty liver. The ICCs of hepatic and renal brightness measurements and the calculated HRI between the two radiologists were 0.892 (95% confidence interval [CI], 0.866 to 0.913), 0.898 (95% CI, 0.873 to 0.918), and 0.681 (95% CI, 0.615 to 0.738) for the first session and 0.920 (95% CI, 0.901 to 0.936), 0.874 (95% CI, 0.844 to 0.898), and 0.579 (95% CI, 0.497 to 0.650) for the second session, respectively; the results ranged from moderate to excellent agreement. Using the same task, the ICCs of the hepatic and renal measurements and the calculated HRI between the average values of the two radiologists and DCNN were 0.919 (95% CI, 0.899 to 0.935), 0.916 (95% CI, 0.895 to 0.932), and 0.734 (95% CI, 0.676 to 0.782), respectively, showing high to excellent agreement.Conclusion: Automated quantification of HRI using DCNN can yield HRI measurements similar to those obtained by experienced radiologists in patients with normal or mild fatty liver.
- Open Access
- 1 January 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (1) , 7-22
Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency
In this review of the most recent applications of deep learning to ultrasound imaging, the architectures of deep learning networks are briefly explained for the medical imaging applications of classification, detection, segmentation, and generation. Ultrasonography applications for image processing and diagnosis are then reviewed and summarized, along with some representative imaging studies of the breast, thyroid, heart, kidney, liver, and fetal head. Efforts towards workflow enhancement are also reviewed, with an emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented regarding image quality enhancement, diagnostic support, and improvements in workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.
- 1 January 2021
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 40 (1) , 7-22
Open AccessTechnology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency
In this review of the most recent applications of deep learning to ultrasound imaging, the architectures of deep learning networks are briefly explained for the medical imaging applications of classification, detection, segmentation, and generation. Ultrasonography applications for image processing and diagnosis are then reviewed and summarized, along with some representative imaging studies of the breast, thyroid, heart, kidney, liver, and fetal head. Efforts towards workflow enhancement are also reviewed, with an emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented regarding image quality enhancement, diagnostic support, and improvements in workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.
- 1 February 2015
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 50 (2) , 81-87
A Novel Electrode With Electromagnetic Tip Tracking in Ultrasonography-Guided Radiofrequency Ablation
The objective of this study was to compare the targeting and ablation performance between a newly developed radiofrequency (RF) electrode embedded with an electromagnetic position sensor (EMPS) at the electrode tip and a conventional RF electrode.The institutional animal care and use committee approved this study. The targeting of paint balls within phantoms was performed under ultrasonography guidance by 2 radiologists (beginner vs expert) with an "in-plane" and "out-of-plane" approaches using the new RF electrode and a conventional RF electrode (n = 20 for each method). To evaluate the targeting performance, the electrode placement time and the number of electrode pullbacks for redirection were compared between the 2 electrodes. The ablation performance was also compared by analyzing the ablation volumes in ex vivo bovine and in vivo porcine livers (n = 30 and n = 24, respectively) and the cellular viability of the ablation zone in in vivo specimens.In the phantom study, the RF electrode embedded with an EMPS showed a significantly shorter electrode placement time compared with the conventional RF electrode in both the in-plane and out-of-plane approaches by both radiologists (P < 0.05). The electrode pullback rate for both radiologists was lower in the new RF electrode than in the conventional RF electrode, but it did not reach statistical significance in the in-plane approach by the expert (P = 0.059). The ablation volumes analyzed with and without cellular viability in the ex vivo and in vivo studies were not significantly different between the 2 electrodes (P > 0.05).The RF electrode embedded with an EMPS is faster than the conventional electrode in the electrode placement into the target lesions. The ablation performance is not significantly different between the 2 electrodes.
- 1 February 2015
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 50 (2) , 81-87
A Novel Electrode With Electromagnetic Tip Tracking in Ultrasonography-Guided Radiofrequency Ablation
The objective of this study was to compare the targeting and ablation performance between a newly developed radiofrequency (RF) electrode embedded with an electromagnetic position sensor (EMPS) at the electrode tip and a conventional RF electrode.The institutional animal care and use committee approved this study. The targeting of paint balls within phantoms was performed under ultrasonography guidance by 2 radiologists (beginner vs expert) with an "in-plane" and "out-of-plane" approaches using the new RF electrode and a conventional RF electrode (n = 20 for each method). To evaluate the targeting performance, the electrode placement time and the number of electrode pullbacks for redirection were compared between the 2 electrodes. The ablation performance was also compared by analyzing the ablation volumes in ex vivo bovine and in vivo porcine livers (n = 30 and n = 24, respectively) and the cellular viability of the ablation zone in in vivo specimens.In the phantom study, the RF electrode embedded with an EMPS showed a significantly shorter electrode placement time compared with the conventional RF electrode in both the in-plane and out-of-plane approaches by both radiologists (P < 0.05). The electrode pullback rate for both radiologists was lower in the new RF electrode than in the conventional RF electrode, but it did not reach statistical significance in the in-plane approach by the expert (P = 0.059). The ablation volumes analyzed with and without cellular viability in the ex vivo and in vivo studies were not significantly different between the 2 electrodes (P > 0.05).The RF electrode embedded with an EMPS is faster than the conventional electrode in the electrode placement into the target lesions. The ablation performance is not significantly different between the 2 electrodes.
- 1 January 2015
- Published by Elsevier in European Journal of Radiology
- Vol. 84 (1) , 33-40
Gastrointestinal stromal tumours: Correlation of modified NIH risk stratification with diffusion-weighted MR imaging as an imaging biomarker
- 1 January 2015
- Published by Elsevier in European Journal of Radiology
- Vol. 84 (1) , 33-40
Gastrointestinal stromal tumours: Correlation of modified NIH risk stratification with diffusion-weighted MR imaging as an imaging biomarker