• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.608-610
• /
• 2023

의료 분야에서 AI 모델의 활용이 증가하고 있지만, 모델의 예측 불확실성을 정확하게 평가하고 표현하는 것이 중요하다. 본 연구는 이러한 문제를 해결하기 위해 AI-driven 방식을 제안하며, 특히 의료 영상 변환 모델에 대한 불확실성 표현과 데이터 한계 극복 방법론을 제안한다. 제안된 AI-driven 안저영상 변환 모델은 기존 GAN과는 다르게 구조가 이루어져 있으며, 신뢰도가 낮은 영역을 구분하고 시각화하여 표현할 수 있다. 실험 결과, 제안된 방법은 기존 모델과 비교하여 영상 변환 성능이 크게 향상되었으며, 불확실성에 대한 정확도 평가에서도 AI-driven 방식이 높은 성능을 보인다. 결론적으로, 본 연구는 AI-driven 방식을 통해 의료 AI에서의 불확실성 표현의 가능성을 확인하였으며, 이 방식이 데이터의 한계와 불확실성을 극복할 수 있을 것으로 기대된다.

• Journal of Digital Convergence
• /
• v.18 no.5
• /
• pp.305-315
• /
• 2020

As the incidence and prevalence of dementia increases with our aging population, so does the social burden on our society, which calls for a special emphasis on need for early diagnosis. Thus, efforts are made to prevent dementia and early detection but with current diagnostic measures, these efforts appear futile. As a solution, it is crucial to integrate and standardize healthcare big data and analysis of each index. In order to increase use of large database, the Korea National Assembly passed the Data 3 Act focusing on open-access and sharing of database, but a follow-up legislation is needed a for safer utilization. In this study, we have identified number of foreign of foreign policies through review of prior researches on the topic leading to specific enforcement ordinances tailored to the Data 3 Act for safe access and utilization of database. We also aimed to establish secure process of data collection and disposal as well as governance at the national level to ensure safe utilization of healthcare big data.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.149-156
• /
• 2020

In the Fourth Industrial Revolution, successful cases using big data in various industries are reported. This paper examines cases that successfully use big data in the medical industry to develop the service and draws implications in value that big data create. The related work introduces big data technology in the medical field and cases of eight innovative service in the big data service are explained. In the introduction, the overall structure of the study is mentioned by describing the background and direction of this study. In the literature study, we explain the definition and concept of big data, and the use of big data in the medical industry. Next, this study describes the several cases, such as technologies using national health information and personal genetic information for the study of diseases, personal health services using personal biometric information, use of medical data for efficiency of business processes, and medical big data for the development of new medicines. In the conclusion, we intend to provide direction for the academic and business implications of this study, as well as how the results of the study can help the domestic medical industry.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.66-76
• /
• 2017

In this study, we investigated how to protect personal healthcare information when constructing OMOP (Observational Medical Outcomes Partnership) CDM (Common Data Model). There are two proposed methods; to restrict data corresponding to HIPAA (Health Insurance Portability and Accountability Act) PHI (Protected Health Information) to be extracted to CDM or to disable identification of it. While processing sensitive information is restricted by Korean Personal Information Protection Act and medical law, there is no clear regulation about what is regarded as sensitive information. Therefore, it was difficult to select the sensitive information for protecting personal healthcare information. In order to solve this problem, we defined HIPAA PHI as restriction criterion of Article 23 of the Personal Information Protection Act and maps data corresponding to CDM data. Through this study, we expected that it will contribute to the spread of CDM construction in Korea as providing solutions to the problem of protection of personal healthcare information generated during CDM construction.

• 전기의세계
• /
• v.53 no.4
• /
• pp.59-61
• /
• 2004

컴퓨터 기술의 발전과 데이터 압축 및 전송 기술의 발달로 인하여, 인터넷을 통하여 실시간으로 전송된 음성, 비디오, 생체 신호, 문자, 처방, 의료 영상 등으로 이루어진 멀티미디어 의료 정보가 임상 진료, 의학 연구 및 교육에 활용되고 있다.(중략)

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.153-159
• /
• 2015

With information technology and health care, efficient health data management provides various health services. Health data from hospitals patients and healthy persons use stacked up enables to trace health condition and to manage health effectively and to reduce healthcare cost. In this paper, we design and implement a framework for relaying health data from various hospitals to cloud storage for manage health condition. For efficient authentication of the framework with cloud storage, OAuth2 protocal is adopted. The proposed health data relay framework can be used for developing various health services with the stacked data in the cloud storage.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.12
• /
• pp.3275-3284
• /
• 1998

In this paper, we deseribe a Medical Image Information System. Our system stores and manages 5 dimensional medical image data and provides the 3 dimensional medical data via the Internet. The Internet standard VR format. VRML(Virtual Reality Modeling Language) is used to represent the 3I) medical image data. The 3D images are reconstructed from medical image data which are enerated by medical imaging systems such ans CT(Computerized Tomography). MRI(Magnetic Resonance Imaging). PET(Positron Emission Tomograph), SPECT(Single Photon Emission Compated Tomography). We implemented the medical image information system shich rses a surface-based rendering method for the econstruction of 3D images from 2D medical image data. In order to reduce the size of image files to be transfered via the Internet. The system can reduce more than 50% for the triangles which represent the surfaces of the generated 3D medical images. When we compress the 3D image file, the size of the file can be redued more than 80%. The users can promptly retrieve 3D medical image data through the Internet and view the 3D medical images without a graphical acceleration card, because the images are represented in VRML. The image data are generated by various types of medical imaging systems such as CT, MRI, PET, and SPECT. Our system can display those different types of medical images in the 2D and the 3D formats. The patient information and the diagnostic information are also provided by the system. The system can be used to implement the "Tele medicaine" systems.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.132-137
• /
• 2019

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.

• The KIPS Transactions:PartC
• /
• v.19C no.1
• /
• pp.19-28
• /
• 2012

Wireless sensor network provides services anytime and anywhere they are requested. Especially, medical sensor network based on biosensors is applied a lot to biotechnology and medical engineering. In medical sensor network, people can make their health checked at home free from temporal and spatial constraints. In ubiquitous healthcare environment, people can get instant help even in the emergency, and in hospital, patients can be taken care of efficiently. In this environment, health and life related data are delivered, and the privacy and security of personal data are very important. In this paper, we propose user authentication and data communication mechanism in two modes, normal and urgent situation using cellular phone. Through our proposal, data can be transferred in quick and secure manner.