• Title/Summary/Keyword: 의료 모델

Search Result 853, Processing Time 0.026 seconds

Data Augmentation Method for Deep Learning based Medical Image Segmentation Model (딥러닝 기반의 대퇴골 영역 분할을 위한 훈련 데이터 증강 연구)

  • Choi, Gyujin;Shin, Jooyeon;Kyung, Joohyun;Kyung, Minho;Lee, Yunjin
    • Journal of the Korea Computer Graphics Society
    • /
    • v.25 no.3
    • /
    • pp.123-131
    • /
    • 2019
  • In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

Development of Educational Content for Dental Extraction Skill Training Using Virtual Reality Technology (가상현실 기반의 치아발치 수기 훈련을 위한 교육콘텐츠 개발)

  • Park, Jong-Tae;Kim, Ji Hyo;Lee, Jeong-hyun
    • The Journal of the Korea Contents Association
    • /
    • v.18 no.12
    • /
    • pp.218-228
    • /
    • 2018
  • The purpose of this study was to present a educational content developed for training of dental extraction skill in a virtual environment. The development of the content consists of five steps: learning content analysis, draw a design model, development, test of validity, rectification and complete of the content. We developed the virtual reality (VR) simulator with producing an animation of surgical stages on the 3D models of human face for simulating dental extraction procedure. The results of validity tests for the content were mean 4.81 (SD, 0.72) for interface validity and mean 4.66 (SD, 0.71) for content validity, which represents strong evidence for the validity of the content. The data of the study indicates that the educational content developed for training of dental extraction skill using VR technology can be suitable to improve surgical skill of dental extraction in clinical field. We expect that further development of the education contents based on the VR technology to improve various surgical skills in clinical field will be addressed in the future.

A Study on the Acoustic Analysis Method of the External Ear Canal Using DICOM Images (DICOM 영상을 이용한 외이도 음향해석 방법에 관한 연구)

  • Kim, Hyeong-Gyun
    • Journal of the Korea Convergence Society
    • /
    • v.10 no.3
    • /
    • pp.73-79
    • /
    • 2019
  • This study simulated external ear canal modeling with different external ear canal lengths, vertical flexion angles, and inner/outer diameter ratios using digital imaging and communications in medicine(DICOM) of the head temporal region and measured the acoustic sensitivity. The experiment was performed by increasing the audible frequency for humans by 200 Hz and expressing the frequency constantly transmitted at 1 Pa as the eardrum acoustic volume and presented the measurements by linear and quadratic curve regression analysis. The results showed that the longer the external ear canal length and the higher the ratio of the outer/inner diameter, the faster the acoustic response at lower frequencies. The acoustic sensitivity correlation of the meta-model using regression analysis showed a 77% influence by the external ear canal length and 5% by the external/internal diameter ratio, while the vertical flexion angle did not show a significant relationship. This showed that auditory acoustic sensitivity of humans is a factor that reacts faster at a low frequency when the external ear canal length is longer and when the difference between the outer and inner diameter is higher.

3D Virtual Reality Game with Deep Learning-based Hand Gesture Recognition (딥러닝 기반 손 제스처 인식을 통한 3D 가상현실 게임)

  • Lee, Byeong-Hee;Oh, Dong-Han;Kim, Tae-Young
    • Journal of the Korea Computer Graphics Society
    • /
    • v.24 no.5
    • /
    • pp.41-48
    • /
    • 2018
  • The most natural way to increase immersion and provide free interaction in a virtual environment is to provide a gesture interface using the user's hand. However, most studies about hand gesture recognition require specialized sensors or equipment, or show low recognition rates. This paper proposes a three-dimensional DenseNet Convolutional Neural Network that enables recognition of hand gestures with no sensors or equipment other than an RGB camera for hand gesture input and introduces a virtual reality game based on it. Experimental results on 4 static hand gestures and 6 dynamic hand gestures showed that they could be used as real-time user interfaces for virtual reality games with an average recognition rate of 94.2% at 50ms. Results of this research can be used as a hand gesture interface not only for games but also for education, medicine, and shopping.

Automatic Analysis Model for Support Emergency Medical Helicopter Landing Zone Using Geographic Information System (GIS를 이용한 비상 의료지원 헬리콥터 착륙지점 자동 분석 모델)

  • Park, Jong-kook;Lee, Eun-seok;Kim, Jong-hee;Kim, Jeong-su;Kim, Jong-bae
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2014.05a
    • /
    • pp.338-340
    • /
    • 2014
  • The purpose of this research is to support decision making of emergency rescue system with GIS which selects landing point of emergency rescue for emergency situation on mountains and dropping point when landing is impossible. The area of research was limited to Pocheon-si, Gyeonggi-do. The results were divided into two values; landing point of helicopter on mountains and dropping point. Digital map, forest type map and forest soil map were utilized as fundamental data. Factors of landing point were slope, topographical characteristics, vegetation characteristics and area of helicopter landing point by helicopter data. And, for dropping point, slope and vegetation characteristics were divided as factors and GIS intersect function was utilized for the analysis. But, this research was conducted by excluding factor values of wind direction, wind velocity, etc. In the future, it's necessary to improve effectiveness of the analysis more by making a connection with Meteorological Agency DB.

  • PDF

The Effect of Nurse Work Environment and Reciprocity on Job Embeddedness in the Small and Medium Sized Hospital Nurses (중소병원 간호사의 간호근무환경과 호혜성이 직무배태성에 미치는 영향)

  • Park, Kyung-Im;Kim, Eun-A
    • Journal of Convergence for Information Technology
    • /
    • v.9 no.8
    • /
    • pp.63-73
    • /
    • 2019
  • The purpose of this study is to examine the effects of nursing work environment and reciprocity on job embeddedness in the small and medium size hospital nurses. The data were collected from questionnaires filled out by 206 nurses. Data collection was performed from March 4 to 22, 2019. The collected data were analyzed by SPSS 25.0 program. As a result of the research, the study model accounted for 66.0% of job embeddedness. The most powerful variable affecting job embeddedness was support system of nurse, among sub - variables of nursing work environment. Therefore, nursing managers should improve the nurse's job embeddedness by creating nursing work environment that supports nurses such as salary improvement, professional development and promotion opportunities. In addition, it suggests that improvement of hospital and nursing organization system is needed to maintain cooperative relationship with nursing team or other health care professionals.

Quality Improvement Priorities for Cosmetic Medical Service Using Kano Model and Potential Customer Satisfaction Improvement Index (Kano 모델 및 잠재적 고객만족 개선 지수를 이용한 미용성형의료서비스 품질 개선 우선순위)

  • Park, Youyoung;Jung, Hunsik
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.42 no.3
    • /
    • pp.176-183
    • /
    • 2019
  • The environmental changes in the Korean cosmetic medical service industry in the $21^{st}$ century are forming intense competition among medical institutions due to the quantitative expansion of its market. For stable growth of the cosmetic medical service industry, continuous quality improvement is necessary based on empirical research on the quality of cosmetic medical services rather than external expansion. The purpose of this study is to classify the quality attributes of cosmetic medical service using Kano model and to derive the degree of satisfaction and dissatisfaction of each quality attributes through Customer Satisfaction Coefficient (CSC). Through this, the study identified strategic priorities and suggested specific step-by-step approaches and quality improvement priorities that can increase customer satisfaction using the Potential Customer Satisfaction Improvement Index (PCSI Index). Based on SERVPERF, this study used measurement tools consisting of five dimensions : tangibles, reliability, responsiveness, assurance, and empathy. In addition, it was used of measurement items reconstructed into positive, negative, and satisfaction questions for Kano model analysis, CSC analysis, and PCSI Index analysis. A total of 300 medical consumers who experienced cosmetic medical services for the past one year in medical institutions such as plastic surgery and dermatology were collected with convenient sampling. As a result, urgent items for improving the quality of service using the PCSI Index, 'Consideration for customer benefits' in empathy category was followed by 'Immediate help' and 'Sincere response' in responsiveness category, and 'Understanding customer needs' in empathy category, respectively. That is, it is required to improve human service quality attributes such as empathy and responsiveness rather than physical service quality attributes. This study contributes practically in that it provides specific and discriminatory approaches to improve customer satisfaction on cosmetic medical service quality and suggests improvement priorities.

Suppressing Effects of Ethanol Extract from Dioscoreae Rhizoma on atope Dermatitis (부채마 에탄올 추출물의 아토피 피부염 억제 효과)

  • Do, Young-Bog;Song, Young-Soon
    • Journal of Digital Convergence
    • /
    • v.17 no.8
    • /
    • pp.257-264
    • /
    • 2019
  • This study was conducted to investigate the effect of 70% ethanol extract (DR) on the mast cell-mediated allergic contact dermatitis induced by dinitrofluorobenzene in BALB / c mice, which affects the cell activity by antigen in RBL-2H3 mast cells Respectively. The ethanol extracts of RBL-2H3 cells activated by DNP-HSA and anti-DNP IgE antibodies inhibited the secretion of ${\beta}$-hexosaminidase, histamine, and IL-4 and $TNF-{\alpha}$ Production was suppressed. In the DNFB-induced contact allergic dermatitis animal model, treatment with ethanol extract reduced ear swelling and inhibited serum histamine and IL-4 secretion, and DR treatment effectively prevented mast cell infiltration in dermatitis-induced areas. As a result, the ethanol extract may be used as a therapeutic agent for mast cell-mediated allergic diseases such as atopic dermatitis.

Radiological Impact Assessment for Radioactive Concrete in Dismantling of the Medical Cyclotron (의료용 사이클로트론 해체 시 발생되는 방사화 콘크리트의 방사선학적 영향평가)

  • Jang, Donggun;Shin, Sanghwa
    • Journal of the Korean Society of Radiology
    • /
    • v.13 no.1
    • /
    • pp.73-80
    • /
    • 2019
  • Neutrons are generated by the nuclear reaction, which is absorbed into the concrete wall and causes the activation during cyclotron operation. The purpose of this study is to investigate the effect of neutron activation and radiative concrete on concrete type. This experiment used Monte Carlo simulation and RESRAD model. The results of the experiment showed that the higher the content of Fe in concrete, the greater the shielding rate. The effect of $^{56}Fe(n,\;2np)^{54}Mn$ reaction on workers is also increased. However, radioactive nuclides have low activity and have very low impact on workers. Radioactive concrete should be treated as general wastes with less than its self-disposal tolerance level, and it should be recycled to the surface such as road repair rather than landfill to minimize the effect of $^{14}C$.

Improvement Effect of the Water Extract from the Root of Cirsium japonicum var. ussuriense on Type II Collagen-induced Rheumatoid Arthritis Animal Models (엉겅퀴 뿌리 물 추출물의 류마티스 관절염 동물 모델에 대한 개선 효과)

  • Nho, Jong Hyun;Lee, Hyeun Joo;Lee, E Na;Woo, Kyeong Wan;Jang, Ji Hun;Kim, Sun Ra;Cho, Hyun Woo;Noh, Se Eung;Jung, Ho Kyung
    • Korean Journal of Medicinal Crop Science
    • /
    • v.28 no.6
    • /
    • pp.471-480
    • /
    • 2020
  • Background: The roots of Cirsium japonicum var. ussuriense (RCJ) have been used as traditional medicine in Korea for hematuria and hematemesis. These extracts exert anti-oxidative and anti-inflammatory effects by scavenging for free radical and regulating the inflammatory response. However, the effect of RCJ on rheumatoid arthritis (RA) has not been elucidated. Thus, we evaluated the water extract of RCJ (WRCJ) using type II collagen-induced RA models. Methods and Results: RA was induced by immunization with type II collagen. All experimental materials were orally administered daily for three weeks. The positive control group was administered with 0.2 mg/kg methotrexate (n = 7), while the experimental group was administered with WRCJ (100 or 500 mg/kg, n = 7). Serum levels of TNF-alpha, Interleukin 6 (IL-6), and type II collagen IgG (CII) were measured using ELISA. Administration of 500 mg/kg WRCJ decreased the levels of TNF-alpha, IL-6, and CII. Moreover, WRCJ treatment diminished swelling of hind legs and infiltration of inflammatory cells in RA models' synovial membrane. Conclusions: These results indicate that WRCJ could improve RA, reduce inflammatory indicators and synovial inflammation. However, further experiments are required to determine how WRCJ can influence the signal transduction pathway in RA.