• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1497-1503
• /
• 2020

Inflammatory myofibroblastic tumors (IMTs) are rare. They are characterized by myofibroblastic spindle cell proliferation with a varying degree of inflammatory cell infiltration. IMT can occur in any anatomic location but has been reported in the lung, mesentery, and omentum, mainly in children or young adults. It rarely occurs in the pancreas and is often difficult to distinguish from other tumors, including some malignant ones. Therefore, it can be challenging to make a radiological diagnosis of IMT. Here, we present a case of IMT that occurred in the pancreas head of a middle-aged female. The patient's ultrasonography, computed tomography, and magnetic resonance imaging findings are presented along with a review of the literature.

• Journal of the Korean Society of Radiology
• /
• v.82 no.6
• /
• pp.1628-1633
• /
• 2021

Spinal epidural arteriovenous fistulas (SEDAVFs) are rare spinal vascular malformations that are difficult to diagnose and treat. SEDAVFs can be asymptomatic; however, symptoms can arise from the compression of adjacent nerve roots by dilated vein and perimedullary venous reflux, caused by shunting into the epidural venous plexus. A 31-year-old male presented to our institution with a 2-year history of progressively worsening low-back pain, radiating thigh pain, and sensory changes in his lower extremities. MRI and CT angiography demonstrated dilated epidural vascular lesion compressing the nerve root. The SEDAVF was embolized with multiple coils, which alleviated the nerve root compression from the engorged venous varix and improved the patient's radiculopathy. Our experience from this case shows that endovascular coil embolization using the transarterial approach can be an effective treatment for SEDAVF and an alternative to surgical ligations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.177-184
• /
• 2024

In the situation of increasing data at fast speed, we use all kinds of complex ensemble and deep learning algorithms to get the highest accuracy. It's sometimes questionable how these models predict, classify, recognize, and track unknown data. Accomplishing this technique and more has been and would be the goal of intensive research and development in the data science community. A variety of reasons, such as lack of data, imbalanced data, biased data can impact the decision rendered by the learning models. Many models are gaining traction for such interpretations. Now, LIME and SHAP are commonly used, in which are two state of the art open source explainable techniques. However, their outputs represent some different results. In this context, this study introduces a coupling technique of LIME and Shap, and demonstrates analysis possibilities on the decisions made by LightGBM and Keras models in classifying a transaction for fraudulence on the IEEE CIS dataset.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.186-191
• /
• 2023

Data processing techniques play a critical role in decision-making, including handling missing and outlier data, prediction, and recommendation models. This requires a clear explanation of the validity, reliability, and accuracy of all processes and results. In addition, it is necessary to solve data problems through explainable models using decision trees, inference, etc., and proceed with model lightweight by considering various types of learning. The multi-layer mining classification method that applies the sixth principle is a method that discovers multidimensional relationships between variables and attributes that occur frequently in transactions after data preprocessing. This explains how to discover significant relationships using mining on transactions and model the data through regression analysis. It develops scalable models and logistic regression models and proposes mining techniques to generate class labels through data cleansing, relevance analysis, data transformation, and data augmentation to make explanatory decisions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.21-28
• /
• 2024

Nowadays, based on the 4th Industrial Revolution, by using the CHATGPT function and 3D virtual reality technology, anyone can easily open a virtual environment WEB-based, smart tourism OPEN source and travel destination without having to directly visit the travel location in the real world. Using the API function, it provides the convenience of virtual tourism. However, this function does not work if the travel transportation system is suddenly changed due to sudden bad weather, travel operation information cannot be checked in real time, and due to a lack of flight cancellation information and passenger ship operation information, it cannot be used until the plane or ferry departs normally. A very inconvenient problem arises where you have to wait a long time in the waiting room. Therefore, in this paper, in order to solve this problem, automatic duty-free product information and automatic product payment functions were added even when passenger ship cancellations and operation information suddenly occur due to bad weather and multiple products are purchased during the trip. In addition, the computer simulation experiment was conducted on a WEB basis so that anyone can conveniently travel smartly.

• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.153-163
• /
• 2024

Despite the increasing hacking threats and security threats as IT technology advances and many companies adopt security solutions, cyberattacks and threats still persist for years. APT attack is a technique of selecting a specific target and continuing to attack. The threat of an APT attack uses all possible means through the electronic network to perform APT for years. Zero-day attacks, malicious code distribution, and social engineering techniques are performed, and some of them directly invade companies. These techniques have been in effect since 2000, and are similarly used in voice phishing, especially for social engineering techniques. Therefore, it is necessary to study countermeasures against APT attacks. This study analyzes the attack cases of Korean-based APT groups in Korea and suggests the correct method of using intelligence to analyze APT attack groups.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.799-808
• /
• 2024

In this paper, a method (phase weighting) is presented to achieve high-gain radiation performance and dual-beamforming functionality based on a reflectarray antenna system. The proposed method aims to mitigate the beam overlap phenomenon by implementing split dual-beamforming, using phase weighting that induces differential electric field strength between sub-arrays. To validate the proposed method, a numerical model for analyzing the radiation characteristics of the reflectarray antenna was developed, and a comparative analysis was conducted with a conventional sub-array-based dual-beamforming method. Simulation results under various conditions confirmed that the proposed method not only improves the beam overlap phenomenon but also efficiently forms split dual beams across a range of required beam steering angles.

• Journal of the Korean Society of Radiology
• /
• v.85 no.5
• /
• pp.861-882
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond the field of natural language processing. Owing to their extensive pre-training using vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without the need for additional fine-tuning. Importantly, LLMs are on a trajectory of rapid evolution, addressing challenges such as hallucination, bias in training data, high training costs, performance drift, and privacy issues, along with the inclusion of multimodal inputs. The concept of small, on-premise open source LLMs has garnered growing interest, as fine-tuning to medical domain knowledge, addressing efficiency and privacy issues, and managing performance drift can be effectively and simultaneously achieved. This review provides conceptual knowledge, actionable guidance, and an overview of the current technological landscape and future directions in LLMs for radiologists.

• The Journal of the Korean bone and joint tumor society
• /
• v.11 no.2
• /
• pp.168-174
• /
• 2005

Purpose: We experienced 8 cases of osteoid osteoma arising around hip joint which had some characteristics that differ from those arising on long bone. we reports the characteristics of osteoid osteoma arising around the hip joint. Materials and Methods: 8 cases of osteoid osteoma were diagnosed during 1985 to 2004 at hanyang university hospital. all cases were comfirmed patholgically. 6 cases were male, 2 cases were female patients. The mean age was 17 years old (ranged from 8 to 29). They occurred in intertrochanteric area (4 cases), subtrochanteric area (2 cases), acetabulum (1 case) and femoral neck (1 case). We used radiologic tools including magnetic resonance image, computed tomography, bone scintigraphy. clinicopathologic test including erythrocyte sedimentation rate and Creactive protein. Results: The patients expressed various symptoms including thigh pain, knee pain, low back pain and radiating pain respectively. 2 patients had experienced operation on knee joint. 3 patients showed limping gait. Aspirin relieved the pain in 3 patients. The difference in circumference was 1cm between both thighs in 2 cases. Conclusion: Patients with osteoid osteoma arising around hip joint which have various symptoms such as severe knee pain and claudication, differ from infectious disease by clinicopathologic test including erythrocyte sedimentation rate and C- reactive protein and had better diagnostic result in computed tomography.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.51-56
• /
• 2003

The structuring of Web information supports a strong user side viewpoint that a user wants his/her own needs on snooping a specific Web site. Not only the depth first algorithm or the breadth-first algorithm, but also the Web information is abstracted to a hierarchical structure. A prototype system is suggested in order to visualize and to represent a semantic significance. As a motivating example, the Web test site is suggested and analyzed with respect to several keywords. As a future research, the Web site model should be extended to the whole WWW and an accurate assessment function needs to be devised by which several suggested models should be evaluated.