Jae Ho Oh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jae Ho Oh has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chang Hyun Lee
Department of Physical Medicine and Rehabilitation, Seoul Medical Center, Seoul, Korea
2 shared publications - Duk-Joo Lee
Division of Medical Oncology and Hematology, Department of Internal Medicine, Seoul Medical Center, Seoul, Korea
1 shared publication - Ga Yang Shim
Department of Physical Medicine & Rehabilitation, Kyung Hee University Hospital, College of Medicine, Kyung Hee University, Seoul 02447, Republic of Korea
1 shared publication - Hee Dong Park
Department of Research Institute, Seoul Medical Center, Seoul, Korea
1 shared publication - Hyun Jung Jun
Division of Medical Oncology and Hematology, Department of Internal Medicine, Seoul Medical Center, Seoul, Korea
1 shared publication - Hyunchul An
Department of Emergency Medicine, Pohang SeMyeong Christianity Hospital, Pohang, Korea
1 shared publication
Latest Publications
- Open Access
- 31 August 2024
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 48 (4) , 271-280
Extensive Multilabel Classification of Brain MRI Scans for Infarcts Using the Swin UNETR Architecture in Deep Learning Applications
Objective: To distinguish infarct location and type with the utmost precision using the advantages of the Swin UNEt TRansformers (Swin UNETR) architecture.Methods: The research employed a two-phase training approach. In the first phase, the Swin UNETR model was trained using the Ischemic Stroke Lesion Segmentation Challenge (ISLES) 2022 dataset, which included cases of acute and subacute infarcts. The second phase involved training with data from 309 patients. The 110 categories result from classifying infarcts based on 22 specific brain regions. Each region is divided into right and left sides, and each side includes four types of infarcts (acute, acute lacunar, subacute, subacute lacunar). The unique architecture of Swin UNETR, integrating elements of both the transformer and u-net designs with a hierarchical transformer computed with shifted windows, played a crucial role in the study.Results: During Swin UNETR training with the ISLES 2022 dataset, batch loss decreased to 0.8885±0.1897, with training and validation dice scores reaching 0.4224±0.0710 and 0.4827±0.0607, respectively. The optimal model weight had a validation dice score of 0.5747. In the patient data model, batch loss decreased to 0.0565±0.0427, with final training and validation accuracies of 0.9842±0.0005 and 0.9837±0.0010.Conclusion: The results of this study surpass the accuracy of similar studies, but they involve the issue of overfitting, highlighting the need for future efforts to improve generalizability. Such detailed classifications could significantly aid physicians in diagnosing infarcts in clinical settings.
- 31 August 2024
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 48 (4) , 271-280
Open AccessExtensive Multilabel Classification of Brain MRI Scans for Infarcts Using the Swin UNETR Architecture in Deep Learning Applications
Objective: To distinguish infarct location and type with the utmost precision using the advantages of the Swin UNEt TRansformers (Swin UNETR) architecture.Methods: The research employed a two-phase training approach. In the first phase, the Swin UNETR model was trained using the Ischemic Stroke Lesion Segmentation Challenge (ISLES) 2022 dataset, which included cases of acute and subacute infarcts. The second phase involved training with data from 309 patients. The 110 categories result from classifying infarcts based on 22 specific brain regions. Each region is divided into right and left sides, and each side includes four types of infarcts (acute, acute lacunar, subacute, subacute lacunar). The unique architecture of Swin UNETR, integrating elements of both the transformer and u-net designs with a hierarchical transformer computed with shifted windows, played a crucial role in the study.Results: During Swin UNETR training with the ISLES 2022 dataset, batch loss decreased to 0.8885±0.1897, with training and validation dice scores reaching 0.4224±0.0710 and 0.4827±0.0607, respectively. The optimal model weight had a validation dice score of 0.5747. In the patient data model, batch loss decreased to 0.0565±0.0427, with final training and validation accuracies of 0.9842±0.0005 and 0.9837±0.0010.Conclusion: The results of this study surpass the accuracy of similar studies, but they involve the issue of overfitting, highlighting the need for future efforts to improve generalizability. Such detailed classifications could significantly aid physicians in diagnosing infarcts in clinical settings.
- Open Access
- 30 April 2019
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 43 (2) , 163-177
Duration of Treatment Effect of Extracorporeal Shock Wave on Spasticity and Subgroup-Analysis According to Number of Shocks and Application Site: A Meta-Analysis
To investigate duration of the treatment effect of extracorporeal shockwave therapy (ESWT) on spasticity levels measured with Modified Ashworth Scale (MAS) regardless of the patient group (stroke, multiple sclerosis, and cerebral palsy) and evaluate its spasticity-reducing effect depending on the number of shocks and site of application. PubMed, EMBASE, the Cochrane Library, and Scopus were searched from database inception to February 2018. Randomized controlled trials and cross-over trials were included. All participants had spasticity regardless of cause. ESWT was the main intervention and MAS score was the primary outcome. Among 122 screened articles, 9 trials met the inclusion criteria. The estimate of effect size showed statistically significant MAS grade reduction immediately after treatment (standardized mean difference [SMD]=-0.57; 95% confidence interval [CI], -1.00 to -0.13; p=0.012), 1 week after (SMD=-1.81; 95% CI, -3.07 to -0.55; p=0.005), 4 weeks after (SMD=-2.35; 95% CI, -3.66 to -1.05; p<0.001), and 12 weeks after (SMD=-1.07; 95% CI, -2.04 to -0.10; p=0.03). Meta-regression and subgroup analysis were performed for the 'immediately after ESWT application' group. The prediction equation obtained from metaregression was -1.0824+0.0002* (number of shocks), which was not statistically significant. Difference in MAS grade reduction depending on site of application was not statistically significant either in subgroup analysis (knee and ankle joints vs. elbow, wrist, and finger joints). ESWT effectively reduced spasticity levels measured with MAS regardless of patient group. Its effect maintained for 12 weeks. The number of shocks or site of application had no significant influence on the therapeutic effect of ESWT in reducing spasticity. Ongoing trials with ESWT are needed to address optimal parameters of shock wave to reduce spasticity regarding intensity, frequency, and numbers.
- 30 April 2019
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 43 (2) , 163-177
Open AccessDuration of Treatment Effect of Extracorporeal Shock Wave on Spasticity and Subgroup-Analysis According to Number of Shocks and Application Site: A Meta-Analysis
To investigate duration of the treatment effect of extracorporeal shockwave therapy (ESWT) on spasticity levels measured with Modified Ashworth Scale (MAS) regardless of the patient group (stroke, multiple sclerosis, and cerebral palsy) and evaluate its spasticity-reducing effect depending on the number of shocks and site of application. PubMed, EMBASE, the Cochrane Library, and Scopus were searched from database inception to February 2018. Randomized controlled trials and cross-over trials were included. All participants had spasticity regardless of cause. ESWT was the main intervention and MAS score was the primary outcome. Among 122 screened articles, 9 trials met the inclusion criteria. The estimate of effect size showed statistically significant MAS grade reduction immediately after treatment (standardized mean difference [SMD]=-0.57; 95% confidence interval [CI], -1.00 to -0.13; p=0.012), 1 week after (SMD=-1.81; 95% CI, -3.07 to -0.55; p=0.005), 4 weeks after (SMD=-2.35; 95% CI, -3.66 to -1.05; p<0.001), and 12 weeks after (SMD=-1.07; 95% CI, -2.04 to -0.10; p=0.03). Meta-regression and subgroup analysis were performed for the 'immediately after ESWT application' group. The prediction equation obtained from metaregression was -1.0824+0.0002* (number of shocks), which was not statistically significant. Difference in MAS grade reduction depending on site of application was not statistically significant either in subgroup analysis (knee and ankle joints vs. elbow, wrist, and finger joints). ESWT effectively reduced spasticity levels measured with MAS regardless of patient group. Its effect maintained for 12 weeks. The number of shocks or site of application had no significant influence on the therapeutic effect of ESWT in reducing spasticity. Ongoing trials with ESWT are needed to address optimal parameters of shock wave to reduce spasticity regarding intensity, frequency, and numbers.
- Open Access
- 1 January 2018
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 42 (1) , 166-174
Rehabilitation of Advanced Cancer Patients in Palliative Care Unit
Lee CH, et al. Ann Rehabil Med. 2018 Feb;42(1):166-174. https://doi.org/10.5535/arm.2018.42.1.166
- 1 January 2018
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 42 (1) , 166-174
Open AccessRehabilitation of Advanced Cancer Patients in Palliative Care Unit
Lee CH, et al. Ann Rehabil Med. 2018 Feb;42(1):166-174. https://doi.org/10.5535/arm.2018.42.1.166
- Open Access
- 1 January 2017
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 41 (1) , 158-161
Hypothermia Presenting in Wernicke Encephalopathy: A Case Report
Hong SH, et al. Ann Rehabil Med. 2017 Feb;41(1):158-161. https://doi.org/10.5535/arm.2017.41.1.158
- 1 January 2017
- Published by Korean Academy of Rehabilitation Medicine in Annals of Rehabilitation Medicine
- Vol. 41 (1) , 158-161
Open AccessHypothermia Presenting in Wernicke Encephalopathy: A Case Report
Hong SH, et al. Ann Rehabil Med. 2017 Feb;41(1):158-161. https://doi.org/10.5535/arm.2017.41.1.158