Jae Won Seo

Ms. Jae Won Seo

Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and Technology (GAIHST), Gachon University, Seongnam, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 July 2021 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJae Won Seo
Jae Won Seo
Sang Heon LimSang Heon Lim
Sang Heon Lim
JJJin Gyo Jeong
Jin Gyo Jeong
YKYoung Jae Kim
Young Jae Kim
KKKwang Gi Kim
Kwang Gi Kim
JJJi Young Jeon
Ji Young Jeon
The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U-Net model, with an average sensitivity of 0.934 (± 0.086), an average specificity of 0.997 (± 0.002), an average accuracy of 0.987 (± 0.005), and an average dice similarity coefficient of 0.923 (± 0.073). We then generated 1134 data points on the images of three vertebral bodies by labeling each segment of the segmented vertebral body. These were used in the vertebral compression measurement model based on linear regression and multi-scale residual dilated blocks. The model yielded an average mean absolute error of 2.637 (± 1.872) (%), an average mean square error of 13.985 (± 24.107) (%), and an average root mean square error of 3.739 (± 2.187) (%) in fractured vertebral body data. The proposed algorithm has significant potential for aiding the diagnosis of vertebral compression fractures.

21 January 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
JHJung Han Hwang
Jung Han Hwang
JSJae Won Seo
Jae Won Seo
JKJeong Ho Kim
Jeong Ho Kim
SPSuyoung Park
Suyoung Park
YKYoung Jae Kim
Young Jae Kim
KKKwang Gi Kim
Kwang Gi Kim
In this study, we aimed to investigate quantitative differences in performance in terms of comparing the automated classification of deep vein thrombosis (DVT) using two categories of artificial intelligence algorithms: deep learning based on convolutional neural networks (CNNs) and conventional machine learning. We retrospectively enrolled 659 participants (DVT patients, 282; normal controls, 377) who were evaluated using contrast-enhanced lower extremity computed tomography (CT) venography. Conventional machine learning consists of logistic regression (LR), support vector machines (SVM), random forests (RF), and extreme gradient boosts (XGB). Deep learning based on CNN included the VGG16, VGG19, Resnet50, and Resnet152 models. According to the mean generated AUC values, we found that the CNN-based VGG16 model showed a 0.007 higher performance (0.982 ± 0.014) as compared with the XGB model (0.975 ± 0.010), which showed the highest performance among the conventional machine learning models. In the conventional machine learning-based classifications, we found that the radiomic features presenting a statistically significant effect were median values and skewness. We found that the VGG16 model within the deep learning algorithm distinguished deep vein thrombosis on CT images most accurately, with slightly higher AUC values as compared with the other AI algorithms used in this study. Our results guide research directions and medical practice.

18 January 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJae Won Seo
Jae Won Seo
SPSuyoung Park
Suyoung Park
YKYoung Jae Kim
Young Jae Kim
JHJung Han Hwang
Jung Han Hwang
SYSung Hyun Yu
Sung Hyun Yu
KKKwang Gi Kim
Kwang Gi Kim
Early diagnosis of deep venous thrombosis is essential for reducing complications, such as recurrent pulmonary embolism and venous thromboembolism. There are numerous studies on enhancing efficiency of computer-aided diagnosis, but clinical diagnostic approaches have never been considered. In this study, we evaluated the performance of an artificial intelligence (AI) algorithm in the detection of iliofemoral deep venous thrombosis on computed tomography angiography of the lower extremities to investigate the effectiveness of using the clinical approach during the feature extraction process of the AI algorithm. To investigate the effectiveness of the proposed method, we created synthesized images to consider practical diagnostic procedures and applied them to the convolutional neural network-based RetinaNet model. We compared and analyzed the performances based on the model’s backbone and data. The performance of the model was as follows: ResNet50: sensitivity = 0.843 (± 0.037), false positives per image = 0.608 (± 0.139); ResNet152 backbone: sensitivity = 0.839 (± 0.031), false positives per image = 0.503 (± 0.079). The results demonstrated the effectiveness of the suggested method in using computed tomography angiography of the lower extremities, and improving the reporting efficiency of the critical iliofemoral deep venous thrombosis cases.

5 February 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJae Won Seo
Jae Won Seo
YKYoung Jae Kim
Young Jae Kim
KKKwang Gi Kim
Kwang Gi Kim
Employing two standard mammography views is crucial for radiologists, providing comprehensive insights for reliable clinical evaluations. This study introduces paired mammogram view based-network(PMVnet), a novel algorithm designed to enhance breast lesion detection by integrating relational information from paired whole mammograms, addressing the limitations of current methods. Utilizing 1,636 private mammograms, PMVnet combines cosine similarity and the squeeze-and-excitation method within a U-shaped architecture to leverage correlated information. Performance comparisons with single view-based models with VGGnet16, Resnet50, and EfficientnetB5 as encoders revealed PMVnet’s superior capability. Using VGGnet16, PMVnet achieved a Dice Similarity Coefficient (DSC) of 0.709 in segmentation and a recall of 0.950 at 0.156 false positives per image (FPPI) in detection tasks, outperforming the single-view model, which had a DSC of 0.579 and a recall of 0.813 at 0.188 FPPI. These findings demonstrate PMVnet’s effectiveness in reducing false positives and avoiding missed true positives, suggesting its potential as a practical tool in computer-aided diagnosis systems. PMVnet can significantly enhance breast lesion detection, aiding radiologists in making more precise evaluations and improving patient outcomes. Future applications of PMVnet may offer substantial benefits in clinical settings, improving patient care through enhanced diagnostic accuracy.

15 May 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJae Won Seo
Jae Won Seo
SPSungJoon Park
SungJoon Park
YKYoung Jae Kim
Young Jae Kim
JKJung-Youn Kim
Jung-Youn Kim
KKKwang Gi Kim
Kwang Gi Kim
YYYoung-Hoon Yoon
Young-Hoon Yoon
In the fast-paced emergency departments, where crises unfold unpredictably, the systematic prioritization of critical patients based on a severity classification is vital for swift and effective treatment. This study aimed to enhance the quality of emergency services by automatically categorizing the severity levels of incoming patients using AI-powered natural language processing (NLP) algorithms to analyze conversations between medical staff and patients. The dataset comprised 1,028 transcripts of bedside conversations within emergency rooms. To verify the robustness of the models, we performed tenfold cross-validation. Based on the area under the receiver operating characteristic curve (AUROC) values, the support vector machine achieved the best performance among the term frequency-inverse document frequency-based conventional machine learning models with an AUROC of 0.764 (95% CI 0.019). Among the neural network models, multilayer perceptron performed with an AUROC of 0.759 (± 0.024). This research explored methods for automatically classifying patient severity using real-world conversations, including those with nonsensical and confused content. To achieve this, artificial intelligence algorithms that consider the frequency and order of words used in the conversation were employed alongside neural network models. Our findings have the potential to significantly contribute to alleviating overcrowding in emergency departments of hospitals, with future extensions involving highly efficient large language models. The results suggest that a fluid and immediate response to urgent situations, a reduction in patient waiting time, and effectively addressing the special circumstances of the emergency room environment can be achieved using this approach.

11 November 2026 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
YKYe Jin Kim
Ye Jin Kim
JSJae Won Seo
Jae Won Seo
YKYoung Jae Kim
Young Jae Kim
KKKwang Gi Kim
Kwang Gi Kim