Test-retest repeatability of ultrasonographic shear wave elastography in a rat liver fibrosis model: toward a quantitative biomarker for preclinical trials

신용빈,허지미,함수정,조영철,최윤석,우동철,이정진,김경원 대한초음파의학회 2021 ULTRASONOGRAPHY Vol.40 No.1

Purpose: This study evaluated the test-retest repeatability and measurement variability of ultrasonographic shear wave elastography (SWE) for liver stiffness in a rat liver fibrosis model. Methods: In 31 Sprague-Dawley rats divided into three groups (high-dose, low-dose, and control), liver fibrosis was induced by intraperitoneal administration of thioacetamide for 8 weeks. A dedicated radiographer performed SWE to measure liver stiffness in kilopascals in two sessions at a 3-day interval. We calculated correlations between liver stiffness and histopathologic results, measurement variability in each session using coefficients of variation (CoVs) and interquartile/median (IQR/M), and test-retest repeatability between both sessions using the repeatability coefficient. Results: Different levels of liver fibrosis in each group were successfully induced in the animal model. The mean liver stiffness values were 8.88±1.48 kPa in the control group, 11.62±1.70 kPa in the low-dose group, and 11.91±1.73 kPa in the high-dose group. The correlation between collagen areas and liver stiffness values was moderate (r=0.6). In all groups, the second session yielded lower CoVs (i.e., more reliable results) for liver stiffness than the first session, suggesting a training effect for the operator. The mean IQR/M values were also lower in the second session than in the first session, which had four outliers (0.21 vs. 0.12, P<0.001). The test-retest repeatability coefficient was 3.75 kPa and decreased to 2.82 kPa after removing the four outliers. Conclusion: The use of ultrasonographic SWE was confirmed to be feasible and repeatable for evaluating liver fibrosis in preclinical trials. Operator training might reduce variability in liver stiffness measurements.

Guided Filter를 이용한 GA-Net Stereo Matching 개선

신용빈,허원석,장하준,임유나,이동해,이정진 한국차세대컴퓨팅학회 2020 한국차세대컴퓨팅학회 논문지 Vol.16 No.1

두 대의 카메라의 양안 시차를 이용해 깊이를 판별하는 stereo matching 분야에서는 최근에 개발되어 가장 효율적 인 알고리즘인 GA-Net이 존재한다. 본 논문에서는 Guided filter라는 경계 처리 알고리즘을 이용해 GA-Net에서 얻어낸 결과를 개선하는 방법을 제안한다. GA-Net에서 얻어낸 결과와 원본 스테레오 이미지를 Guided filter로 합성해 세밀한 경계를 이전보다 정확하게 처리할 수 있는 방법을 제시한다. 실험 결과 GA-Net에서 얻어진 결과는 Guided filter를 사용하여 평균 오차가 16.3% 감소하였다. 또한, Guided filter에서 사용자가 설정해야 하는 파 라미터를 변화하면서 결과를 측정해 파라미터의 변화에 대한 결과 이미지의 경향성을 분석하였다. In the field of stereo matching, the depth is determined by the disparities between two cameras and GA-Net shows the most accurate performance. In this paper, we improve the depth results from GA-Net using guided filtering as an edge enhancement technique. Depth results from GA-Net and original stereo images are merged to produce more detailed depth images. Experimental results showed that the average error of the depth acquired by guided filter was decreased by 16.3%. We analyzed the depth results by controlling user-defined parameters in guided filtering.

Recent Issues on Body Composition Imaging for Sarcopenia Evaluation

이고은,신용빈,허지미,성유섭,In-Seob Lee,Kwon-Ha Yoon,김경원 대한영상의학회 2019 Korean Journal of Radiology Vol.20 No.2

Recently, sarcopenia has garnered renewed interest. Sarcopenia is a disease characterized by decreased skeletal muscle mass and strength/function, which can impair the quality of life and increase physical disability, adverse metabolic effects, and mortality. Imaging tools for evaluating and diagnosing sarcopenia have developed rapidly. Radiologists should be aware of sarcopenia and its clinical implications. We review current knowledge about sarcopenia, its pathophysiological impact, and advantages and disadvantages of methods for evaluation of sarcopenia focusing on body composition imaging modalities such as whole-body dual-energy X-ray absorptiometry, CT, and MRI. Controversial issues are discussed, including the lack of consensus and standardization of the disease definition, imaging modality, measurement methods, and diagnostic cutoff points.

감정 인식 및 강화학습 기법을 이용한 사용자 맞춤형 협동 로봇 모션 생성

최재원,당반치엔,신용빈,길기종,김동완,김종욱 한국지능시스템학회 2017 한국지능시스템학회논문지 Vol.27 No.6

Recently, in the era of the fourth industrial revolution, collaborative robot technology that allows workers to work together while working in a robot's work space is developing rapidly. This paper proposes a collaborative robot software agent that enables closer interaction between user and robot by recognizing user's face and facial expression from camera images and learning user's preference about robot's various motions. In this paper, the authors integrated face_recognition package, which is an open source face/emotion recognition package, an artificial neural network learned using TensorFlow, a reinforcement learning agent implemented based on Soar, a cognitive agent architecture, and a Baxter robot that can be controlled by ROS. In the experiment, Baxter robot learns the user's preference for five robot motions (handshake, greeting, joy, rejection, high five) generated and implements the user's favorite motion properly. 최근 4차산업혁명 시대에 접어들면서 작업자가 로봇의 작업공간 안에 있으면서 함께 작업을 할 수 있는 협동 로봇 기술이빠르게 발전하고 있다. 본 논문에서는 이를 위한 기초연구로서, 카메라 영상으로부터 사용자의 얼굴과 표정을 인식하고로봇의 동작에 대한 사용자 개인의 선호도를 학습함으로써 보다 긴밀한 사용자-로봇 간 상호작용이 가능한 협동 로봇소프트웨어 에이전트를 제안한다. 본 논문에서는 오픈소스 얼굴/감정 인식 패키지인 face_recognitionT,e nsorFlow를 이용하여학습한 인공신경망, 인지에이전트 아키텍처인 Soar를 기반으로 구현한 강화학습 에이전트, 로봇운영체제인 ROS로 제어가능한 Baxter 로봇을 연계하였고, 생성 된 5가지 로봇 모션(악수, 인사, 기쁨, 거절, 하이파이브)에 대한 사용자 별 선호도를학습한 Baxter가 사용자 선호 모션을 기억하여 적절히 구현하는 실험 결과를 소개한다

ZnNb₂O<SUB>6</SUB>:RE<SUP>3+</SUP> (RE=Dy, Dy/Sm, Sm) 형광체 분말의 발광 특성

이세빈,안성준,신용빈,조신호 한국표면공학회 2019 한국표면공학회 학술발표회 초록집 Vol.2019 No.11

시각장애인들을 위한 무선 정보 전송 시스템

길기종,손병준,신용빈,김동우,이수진,김종욱,Gil, Ki-Jong,Son, Byoung-June,Shin, Yong-Bin,Kim, Dong-woo,Lee, Su-Jin,Kim, Jong-Wook 대한임베디드공학회 2017 대한임베디드공학회논문지 Vol.12 No.1

This paper proposes a new device for a portable braille device using Atmega128 and solenoid magnets. This braille device is composed of three panels, and each panel has six solenoid dots. This device aims to help the disabled people who cannot communicate with others. As an application example, when a disabled people approach a traffic light, it sends a message via Bluetooth to the proposed device letting people recognize a dangerous area. The message converted from the database is based on standard braille chart.

수술 중 촬영된 2D XA 영상과 수술 전 촬영된 3D CTA 영상의 고속 강체 정합 기법

박태용(Taeyong Park),신용빈(Yongbin Shin),임선혜(Sunhye Lim),이정진(Jeongjin Lee) 한국멀티미디어학회 2013 멀티미디어학회논문지 Vol.16 No.12

Association of Body Composition with Long-Term Survival in Non-metastatic Rectal Cancer Patients

한진수,류효선,박인자,김경원,신용빈,김선옥,임석병,김찬욱,윤용식,이종률,유창식,김진천 대한암학회 2020 Cancer Research and Treatment Vol.52 No.2

Purpose We evaluated the association of body composition with long-term oncologic outcomes in non-metastatic rectal cancer patients. Materials and Methods We included 1,384 patients with stage(y)0-III rectal cancer treated at Asan Medical Center between January 2005 and December 2012. Body composition at diagnosis was measured using abdomino-pelvic computed tomography (CT). Sarcopenia, visceral obesity (VO), and sarcopenic obesity (SO) were defined using CT measured parameters such as skeletal muscle index (total abdominal muscle area, TAMA), visceral fat area (VFA), and VFA/TAMA. Inflammatory status was defined as a neutrophil-lymphocyte ratio of ! 3. Obesity was categorized by body mass index (! 25 kg/m2). Results Among the 1,384 patients, 944 (68.2%) had sarcopenia and 307 (22.2%) had SO. The 5-year overall survival (OS) rate was significantly lower in sarcopenic patients (no sarcopenia vs. sarcopenia; 84% vs. 78%, p=0.003) but the 5-year recurrence-free survival (RFS) rate was not different (77.3% vs. 77.9% p=0.957). Patients with SO showed lower 5-year OS (79.1% vs. 75.5% p=0.02) but no difference in 5-year RFS (p=0.957). Sarcopenia, SO, VO, and obesity were not associated with RFS. However, obesity, SO, age, sex, inflammatory status, and tumor stage were confirmed as independent factors associated with OS on multivariate analysis. In subgroup analysis, association of SO with OS was more prominent in patients with (y)p stage 0-2 and no inflammatory status. Conclusion The presence of SO and a low body mass index at diagnosis are negatively associated with OS in non-metastatic rectal cancer patients.

IoT 디바이스를 이용한 클라우드 플랫폼 기반의 실시간 공장 모니터링 시스템 개발

박건수,트란트렁틴,당 반 치엔,길기종,신용빈,최재원,김종욱 대한임베디드공학회 2018 대한임베디드공학회논문지 Vol.13 No.1

In this paper, we present a proposed monitoring system for smart factories with several aspects, including information gathering, analysis, control, and display that relate to concurrently operation processes in the factory area. This paper proposes a monitoring and management system for industrial automation. In particular, it uses an Internet of Thing (IoT) device with a data protocol unit to convert the industrial protocols and transfer the information on various parameters. In the case of data communication, the proposed monitoring system is designed to support users to remotely manage with the cloud server by implementing conversion between Modbus RTU and Modbus TCP of protocol communications. The proposed communication technique has been verified by experiments.

Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers

김동욱,Hye Young Jang,김경원,신용빈,박성호 대한영상의학회 2019 Korean Journal of Radiology Vol.20 No.3

Objective: To evaluate the design characteristics of studies that evaluated the performance of artificial intelligence (AI) algorithms for the diagnostic analysis of medical images. Materials and Methods: PubMed MEDLINE and Embase databases were searched to identify original research articles published between January 1, 2018 and August 17, 2018 that investigated the performance of AI algorithms that analyze medical images to provide diagnostic decisions. Eligible articles were evaluated to determine 1) whether the study used external validation rather than internal validation, and in case of external validation, whether the data for validation were collected, 2) with diagnostic cohort design instead of diagnostic case-control design, 3) from multiple institutions, and 4) in a prospective manner. These are fundamental methodologic features recommended for clinical validation of AI performance in real-world practice. The studies that fulfilled the above criteria were identified. We classified the publishing journals into medical vs. non-medical journal groups. Then, the results were compared between medical and non-medical journalsResults: Of 516 eligible published studies, only 6% (31 studies) performed external validation. None of the 31 studies adopted all three design features: diagnostic cohort design, the inclusion of multiple institutions, and prospective data collection for external validation. No significant difference was found between medical and non-medical journals. Conclusion: Nearly all of the studies published in the study period that evaluated the performance of AI algorithms for diagnostic analysis of medical images were designed as proof-of-concept technical feasibility studies and did not have the design features that are recommended for robust validation of the real-world clinical performance of AI algorithms.