• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1993년도 춘계학술대회
• /
• pp.125-128
• /
• 1993

We have developed MITS(Medical Information Transmission System) that captures, stores and manages the digitalized medical images and transmit them via LAN, and also have developed DSCW(Dedicated System for Clinical Ward) that enables to review the medical images and clinical laboratory test results transmitted via LAN at clinical ward. They were implemented on the 386 platforms, and interconnected via 10 Mbps LAN between department of radiology and clinical ward.

• Journal of Information Processing Systems
• /
• 제12권4호
• /
• pp.741-753
• /
• 2016

In the medical fields, many efforts have been made to develop and improve Hospital Information System (HIS) including Electronic Medical Record (EMR), Order Communication System (OCS), and Picture Archiving and Communication System (PACS). However, materials generated and used in medical fields have various types and forms. The current HISs separately store and manage them by different systems, even though they relate to each other and contain redundant data. These systems are not helpful particularly in emergency where medical experts cannot check all of clinical materials in the golden time. Therefore, in this paper, we propose a process to build an integrated data model for medical information currently stored in various HISs. The proposed data model integrates vast information by focusing on medical images since they are most important materials for the diagnosis and treatment. Moreover, the model is disease-specific to consider that medical information and clinical materials including images are different by diseases. Two case studies show the feasibility and the usefulness of our proposed data model by building models about two diseases, acute myocardial infarction (AMI) and ischemic stroke.

• Radiation Oncology Journal
• /
• 제37권4호
• /
• pp.259-264
• /
• 2019

Purpose: Accurate localization of the lumpectomy cavity during accelerated partial breast radiation (APBR) is essential for daily setup to ensure the prescribed dose encompasses the target and avoids unnecessary irradiation to surrounding normal tissues. Three-dimensional ultrasound (3D-US) allows direct visualization of the lumpectomy cavity without additional radiation exposure. The purpose of this study was to evaluate the feasibility of 3D-US in daily target localization for APBR. Materials and methods: Forty-seven patients with stage I breast cancer who underwent breast conserving surgery were treated with a 2-week course of APBR. Patients with visible lumpectomy cavities on high quality 3D-US images were included in this analysis. Prior to each treatment, X-ray and 3D-US images were acquired and compared to images from simulation to confirm accurate position and determine shifts. Volume change of the lumpectomy cavity was determined daily with 3D-US. Results: A total of 118 images of each modality from 12 eligible patients were analyzed. The average change in cavity volume was 7.8% (range, -24.1% to 14.4%) on 3D-US from simulation to the end-of-treatment. Based on 3D-US, significantly larger shifts were necessary compared to portal films in all three dimensions: anterior/posterior (p = 7E-11), left/right (p = 0.002), and superior/inferior (p = 0.004). Conclusion: Given that the lumpectomy cavity is not directly visible via X-ray images, accurate positioning may not be fully achieved by X-ray images. Therefore, when the lumpectomy cavity is visible on US, 3D-US can be considered as an alternative to X-ray imaging during daily positioning for selected patients treated with APBR, thus avoiding additional exposure to ionizing radiation.

• 한국산학기술학회논문지
• /
• 제16권1호
• /
• pp.658-665
• /
• 2015

의료영상에서 잡음을 제거하는 것과 명암대비를 좋게하는 것은 화질을 향상시키는 중요한 방법이다. 본 논문에서는 의료영상의 화질 향상을 위해 에지 기반 잡음 제거 방법과 적응적 비선형 히스토그램 스트레칭 알고리즘을 제안한다. 첫째, 웨이블릿 변환을 수행하고 분해된 고주파 부밴드 각각에 대해 Haar 변환을 수행한다. 동시에 수평, 수직, 대각 방향의 Sobel 마스크를 적용하여 방향별 에지를 검출한다. 둘째, 고주파 부밴드에 대해 에지 기반 적응적 문턱치를 이용하여 잡음을 제거한다. 셋째, 적응적 가중치를 이용하여 고주파 부밴드 계수 값을 향상한 후, Haar 역변환 및 웨이블릿 역변환을 수행하여 복원영상을 얻는다. 마지막으로 복원된 영상의 화소 값의 범위가 좁아졌으므로 제안하는 비선형 히스토그램 스트레칭 알고리즘을 이용하여 명암대비가 향상된 영상을 얻는다. 제안한 알고리즘을 낮은 명암대비를 갖는 의료영상에 적용했을 경우 효율적으로 에지를 보존하면서도 시각적으로 우수한 결과를 얻었다.

• 한국멀티미디어학회논문지
• /
• 제15권11호
• /
• pp.1341-1348
• /
• 2012

본 논문에서는 변형된 모젯 변환을 이용하여 의료영상에서 회전된 물체의 회전각을 추출하고 보정하는 새로운 방법을 제안한다. 모젯 변환은 이산 형태의 라돈 변환으로서 변환 영역은 입력 영상에 대한 투영값으로 구성된다. 최근 영상 정보의 압축을 위해 주로 연구되던 모젯 변환을 회전 물체의 보정에 적용하기 위해 본 논문에서는 다음과 같이 모젯 변환을 변형하여 사용한다. 먼저 회전 영상에서 정확한 회전각을 추출하기 위해, 투영선 상의 화소 뿐만 아니라 투영선에 인접한 화소들도 투영값 계산에 반영한다. 그리고 모젯 변환에서의 계산량 감소를 위해 각 투영 방향에 대해 영상의 중심 화소를 통과하는 하나씩의 투영만을 실행한다. 또한 대상 영상이 회전 영상임을 고려하여 영상의 회전 시 삭제되거나 추가되지 않는 관심 영역을 설정하여 이 영역에 대해서만 투영값을 계산한다. 모의실험을 통해 제안된 방법이 다양한 의료 영상의 회전각 추출 및 보정에 매우 효율적임을 알 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제18권3호
• /
• pp.223-231
• /
• 1997

본 논문에서는 3차원 의료 영상의 압축을 위한 인터프레임 부호화 방법을 제안한다. 슬라이스 사이의 변화를 뼈나 조직의 움직임으로 간주하여 움직임 보상 기법을 통해 이전 프레임으로부터 현재 프레임을 예측하고, 변환 부호화를 사용하여 오차 영상을 압축한다. 의료 영상의 슬라이스 사이의 복잡한 변화를 잘 예측하기 위해 동영상 부호화에서 가장 널리 사용되는 블럭 정합 알고리즘 (BMA) 대신 bilinear 변환을 통한 영상 warping을 사용하였다. 이 warping 방법은 슬라이스 사이에서 object가 없어지는 경우 예측 성능이 저하되는데, 이러한 단점을 보완하기 위해 블럭 겹침 움직임 보상 (OBMC) 기법을 결합하였다. 움직임 보상된 오차 영상의 부호화에는 EZW 부호화를 사용하였고, 이 때 각 프레임의 wavelet 계수의 양자화 오차를 동일하게 하여 프레임마다 일정한 화질을 얻도록 하였다. 모의 실험에서 warping을 사용한 인터프레임 부호화는 각 프레임을 독립적으로 부호화하는 방식보다 높은 압축 성능을 보였고, OBMC를 결합함으로써 warping만을 사용했을 때보다 성능이 더 개선되었다.

• 국제물리치료학회지
• /
• 제12권1호
• /
• pp.2261-2266
• /
• 2021

Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of 'Download All Images' and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

• Korean Journal of Radiology
• /
• 제23권4호
• /
• pp.402-412
• /
• 2022

Objective: To evaluate the image quality and lesion detectability of lower-dose CT (LDCT) of the abdomen and pelvis obtained using a deep learning image reconstruction (DLIR) algorithm compared with those of standard-dose CT (SDCT) images. Materials and Methods: This retrospective study included 123 patients (mean age ± standard deviation, 63 ± 11 years; male:female, 70:53) who underwent contrast-enhanced abdominopelvic LDCT between May and August 2020 and had prior SDCT obtained using the same CT scanner within a year. LDCT images were reconstructed with hybrid iterative reconstruction (h-IR) and DLIR at medium and high strengths (DLIR-M and DLIR-H), while SDCT images were reconstructed with h-IR. For quantitative image quality analysis, image noise, signal-to-noise ratio, and contrast-to-noise ratio were measured in the liver, muscle, and aorta. Among the three different LDCT reconstruction algorithms, the one showing the smallest difference in quantitative parameters from those of SDCT images was selected for qualitative image quality analysis and lesion detectability evaluation. For qualitative analysis, overall image quality, image noise, image sharpness, image texture, and lesion conspicuity were graded using a 5-point scale by two radiologists. Observer performance in focal liver lesion detection was evaluated by comparing the jackknife free-response receiver operating characteristic figures-of-merit (FOM). Results: LDCT (35.1% dose reduction compared with SDCT) images obtained using DLIR-M showed similar quantitative measures to those of SDCT with h-IR images. All qualitative parameters of LDCT with DLIR-M images but image texture were similar to or significantly better than those of SDCT with h-IR images. The lesion detectability on LDCT with DLIR-M images was not significantly different from that of SDCT with h-IR images (reader-averaged FOM, 0.887 vs. 0.874, respectively; p = 0.581). Conclusion: Overall image quality and detectability of focal liver lesions is preserved in contrast-enhanced abdominopelvic LDCT obtained with DLIR-M relative to those in SDCT with h-IR.

• 비파괴검사학회지
• /
• 제22권4호
• /
• pp.377-385
• /
• 2002

비전리 방사선을 이용하는 초음파 탐상법은 안전하며 사용이 간편하기 때문에 비파괴검사에서 매우 선호되고 있는 방법이다. 의학적으로 초음파 탐상법은 동일한 원리를 이용하여 인체의 결함 즉 질병의 진단을 위해 유용한 수단 요로 활용되고 있다. 본 논문에서는 초음파 탐상법에 기반한 의료용 초음파 진단의 원리에 대해 개관하고, 그동안 임상적으로 별로 주목받지 못한 초음파 C스캔 영상을 이용한 치밀골의 미세 골절 진단 가능성을 실험적으로 평가하였다. 실험에서는 돼지 대퇴골에 3점 굽힘 힘 (2-4 kN)을 1 mm/min 속도로 가해 미세 골절을 유발하였다. 골절의 정도를 변화하면서 골절에 대한 엑스선 영상과 25 MHz 접속형 초음파 변환기롤 이용하여 C스캔 영상을 취득하였다. 실험 결과 초음파 C 스캔 영상은 기존의 골절 진단법인 엑스선 영상에서는 진단이 어려운 미세한 골절까지 감지할 수 있음을 확인하였다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권3호
• /
• pp.255-262
• /
• 2022

In this study, by analyzing the examination time for each procedure, the appropriate workload of radiologic technologist is analyzed based on the actual examination time in the current clinical setting by comparing with the examination time in the radiology field setting of the health insurance review and assessment service. In addition, this result is introduced into the calculation of relate value units; it was attempted to provide accurate and objective evidence in the field of radiology. From May 2020 to December 2021, the study retrospectively investigated the examination times recorded in the electronic medical record and picture archiving and communication system at 5 tertiary general hospitals and 1 general hospital. The total of 16 examination parts are applied in this study, including the head, sinuses, chest, ribs, abdomen, pelvis, cervical, thoracic, lumbar, shoulder, elbow, wrist, hip, femur, knee, and ankle. The minimum number of images that could be obtained per radiation generator was 3.6 images for one hour, and the maximum was 6.4 images. When 50% median of procedure time is calculated, the minimum number of images that could be obtained was 16.7 images and maximum was 35.3 images; in addition, minimum examination time is 1.7 minutes, and maximum time is 3.6 minutes. In conclusion, it is judged that there will be insufficient explanation time for basic infection instructions such as hand hygiene during the examinations in current clinical practice. It is believed that radiologic technologists will contribute to providing higher-quality of radiation examination services to the public by complying with guidelines for work and setting appropriate workload on their own.