• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2391-2394
• /
• 2003

J2ME service technology has advantage that can embody independent and, more soft system in DICOM 3.0 and medicine reflex administration server, client′s OS that is medical treatment reflex standard in radio Internet. Also, intranet that do web based spread, and develop by system that can alternate existent client-server structure rapidly. Specialty, possibility of improvement is much because is connecting being limited in internet environment that medical equipment and information system of various kinds of machine are wire in medical institution and so on. Because do medical treatment reflex transmission module development applying DICOM technology and filtering techniques of "m-PACS" In this research, existence, by interlock in radio usable Mobile reflex conversion system design and embody. That is, patient′s information which is stored to various systems to be transmited and can give big help in medical examination and treatment to reflex client without being wooed doctor′s interpretation result and so on in place through environment to be radish tentacle bar see.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.99-102
• /
• 2017

illegal medical advertisement have been on the rise, and false and exaggerated medical advertising are increasing the damage to medical consumers. Therefore it is urgent to take countermeasures about this. Thus, this paper try to analyzes the characteristics of general commercial and other medical advertisements and looks for alternatives that can minimize the damage caused by illegal medical advertisements and institutional weaknesses by analyzing the regulatory trends in medical advertising.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.139-152
• /
• 2012

In the medical web forum, people share medical experience and information as patients and patents' families. Some people search medical information written in non-expert language and some people offer words of comport to who are suffering from diseases. Medical web forums play a role of the informative support and the emotional support. We propose the automatic classification model of articles in the medical web forum into the information support and emotional support. We extract text features of articles in web forum using text mining techniques from the perspective of linguistics and then perform supervised learning to classify texts into the information support and the emotional support types. We adopt the Support Vector Machine (SVM), Naive-Bayesian, decision tree for automatic classification. We apply the proposed model to the HealthBoards forum, which is also one of the largest and most dynamic medical web forum.

• Knowledge Management Research
• /
• v.19 no.4
• /
• pp.119-131
• /
• 2018

In this paper, I research the issue of information security for medical information system of each parties. The outflow of the Personal medical information can lead to problems of medical systems and disadvantage to an individual. In this paper, we research the information security based on a blockchain. In addition, I have analyzed blockchain. I suggest a medical information system framework that can help to keep the privacy of patients by using a blockchain network. Also, In this paper try to explain using private blockchain for medical system. Blockchain can keep the integrity and transparency of the medical records. This research, shows how can build the private blockchain for medical records and how to get the integrity of Data from Private Blockchain and Distuributed Ledger Technology.

• Journal of Information Technology Applications and Management
• /
• v.12 no.2
• /
• pp.129-143
• /
• 2005

In recent years, two major streams in medical information systems are：1) system integration among OCS(Order Communication System), EMR(Electronic Medical Record), PACS(Picture Archiving and Communication System), and ERP(Enterprise Resource Planning) and 2) system integration through medical collaboration between East and West medical service providers. One of the characteristics which differentiate the Korean medical industry from the western medical industry is the East-West medical collaboration. In many respects there are many differences between East and West medical treatment. Although East and West medical treatment have developed from different medical philosophies and standards, we assume that the better medical care can be provided by integrating their medical procedures effectively. The two possible approaches to the integration of East and West medical information systems are suggested in this paper：One is loosely coupled model and the other is tightly coupled model. EMR improves the quality of medical record which reflects the quality of clinical practice. It provides more efficient and convenient way of input, retrieval, storage, communication and management of medical data. We abstracted the standard medical procedures from the two medical procedures performed in Daejeon Oriental Hospital and Hehwa Clinic at Daejeon University and also abstracted database schema by analyzing the characteristics of information needed in East-West medical collaboration. Our EMR is composed of two types of data：one is structured data and the other is unstructured data, which are formalized by SOAP(Subjective, Objective, Assessment, Plan) format. Currently the integrated system is implemented and operated successfully for six months.

• Journal of Information Technology Applications and Management
• /
• v.26 no.2
• /
• pp.75-87
• /
• 2019

Currently, the nation's medical industry is changing due to the rapid development of technology. In addition, medical accidents occurring in the medical industry are gradually increasing amid the drastic changes. Therefore, a possible solution to medical accidents in the changing health care industry is needed. Accordingly, this study uses network-centrality analysis to examine the business ecosystem of smart surgical medical systems to find ways to increase the efficiency of surgery as well as the resolution of medical accident problems, and to suggest the direction of development of the medical system in the future from a systematic business ecosystem perspective.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.6
• /
• pp.39-46
• /
• 2019

In the 21st century, medical facility projects are required to operate appropriate digital technologies as the development of technology and the interests of various participants become more complex. In order for architects to successfully lead negotiations among various stakeholder groups, it is necessary to plan for effective communication through appropriate design reflecting their opinions and coordination of conflicts. For this purpose, building information modeling (BIM), which is a method of designing based on knowledge information related to medical facilities in the building database, can respond to change of order promptly and minimizes the occurrence of design errors can do. Recently, BIM technology and cloud computing technology in ICT have been combined and research on cloud BIM has been actively carried out. The use of cloud computing technology in BIM-based healthcare facility projects can effectively support decision making among project participants and has the advantage of sharing and collaborating on various forms of information generated during the design process, regardless of location and time. Therefore, the purpose of this study is to build of system that can support the design of medical facility using cloud computing technology in BIM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1484-1502
• /
• 2023

The medical sector actively changes and implements innovative features in response to technical development and revolutions. Many of the most crucial elements in IoT-connected health services are safeguarding critical patient records from prospective attackers. As a result, BlockChain (BC) is gaining traction in the business sector owing to its large implementations. As a result, BC can efficiently handle everyday life activities as a distributed and decentralized technology. Compared to other industries, the medical sector is one of the most prominent areas where the BC network might be valuable. It generates a wide range of possibilities and probabilities in existing medical institutions. So, throughout this study, we address BC technology's widespread application and influence in modern medical systems, focusing on the critical requirements for such systems, such as trustworthiness, security, and safety. Furthermore, we built the shared ledger for blockchain-based healthcare providers for patient information, contractual between several other parties. The study's findings demonstrate the usefulness of BC technology in IoHT for keeping patient health data. The BDSA-IoHT eliminates 2.01 seconds of service delay and 1.9 seconds of processing time, enhancing efficiency by nearly 30%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.16-37
• /
• 2022

Accurate liver segment segmentation based on radiological images is indispensable for the preoperative analysis of liver tumor resection surgery. However, most of the existing segmentation methods are not feasible to be used directly for this task due to the challenge of exact edge prediction with some tiny and slender vessels as its clinical segmentation criterion. To address this problem, we propose a novel deep learning based segmentation model, called Boundary-Aware Dual Attention Liver Segment Segmentation Model (BADA). This model can improve the segmentation accuracy of liver segments with enhancing the edges including the vessels serving as segment boundaries. In our model, the dual gated attention is proposed, which composes of a spatial attention module and a semantic attention module. The spatial attention module enhances the weights of key edge regions by concerning about the salient intensity changes, while the semantic attention amplifies the contribution of filters that can extract more discriminative feature information by weighting the significant convolution channels. Simultaneously, we build a dataset of liver segments including 59 clinic cases with dynamically contrast enhanced MRI(Magnetic Resonance Imaging) of portal vein stage, which annotated by several professional radiologists. Comparing with several state-of-the-art methods and baseline segmentation methods, we achieve the best results on this clinic liver segment segmentation dataset, where Mean Dice, Mean Sensitivity and Mean Positive Predicted Value reach 89.01%, 87.71% and 90.67%, respectively.