• Korean Journal of Radiology
• /
• 제22권7호
• /
• pp.1213-1224
• /
• 2021

Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. Materials and Methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

• Journal of Radiation Protection and Research
• /
• 제34권1호
• /
• pp.25-30
• /
• 2009

Micro-columnar CsI(Tl) is the most popular scintillator material which is used for many indirect digital X-ray imaging detectors. The light scattering at the surface of micro-columnar CsI(Tl) scintillator was studied to find the correlation between the surface roughness and the resultant image resolution of indirect X-ray imaging detectors. Using a commercially available optical simulation program, Light Tools, MTF (Modulation Transfer Function) curves of the CsI(Tl) film thermally evaporated on glass substrate with different thickness were calculated and compared with the experimental estimation of MTF values by the edge X-ray image method and CCD camera. It was found that the standard deviation value of Gaussian scattering model which is determined by the surface roughness of micro-columns could certainly change the MTF value of image sensors. This model and calculation methodology will be beneficial to estimate the overall performance of indirect X-ray imaging system with CsI(Tl) scintillator film for optimum design depending on its application.

• 전자공학회논문지SC
• /
• 제40권5호
• /
• pp.341-349
• /
• 2003

고속 디지털신호처리기를 사용한 자기공명영상 실시간 대화형 제어기(스펙트로미터)를 개발하였다. 개발린 제어기는 rf 파형과 경사자계 파형을 만들고, 신호 측정을 위한 다중 측정기를 제어한다. TMS320C6701과 간은 높은 계산 능력을 가진 디지털신호처리기를 사용함으로써 복잡한 경사자계파형의 실시간 계산 및 출력이 가능해졌다. 또한 회전 행렬을 실시간으로 계산함으로써 심장과 같이 움직임이 큰 장기의 실시간 영상에서 얻고자하는 평면을 대화식으로 조절이 가능해졌다. 개발된 스펙트로미터를 1.5 테슬라 전신자기공명 영상시스템에 성공적으로 적용하였다. 개발된 스펙트로미터를 고속스핀에코나 echo planar imaging(EPI) 등과 같은 초고속자기공명영상에 적용하여 성능을 검증하였다. 이것은 이들 초고속 자기공명영상기법들이 측정 시간을 단축해주는 대신에 스펙트로미터의 송신부와 수신부 또는 경사자계부간의 동기나 위상에 에러가 있을 경우 문제점을 크게 부각시켜 시스템의 성능 평가에 적합하기 때문이다.

• 대한영상의학회지
• /
• 제84권1호
• /
• pp.75-91
• /
• 2023

전립선영상 판독과 자료체계 버전 2.1에서는 다중 매개 자기공명영상(multiparametric MRI; 이하 mpMRI)을 사용하는 버전 2의 기술적인 변수와 영상 판독 기준이 개정되었다. 이러한 변화를 통해 전립선암 평가의 발전이 예상지만, 어떤 사항들은 아직까지 해결되지 않았고 새로운 문제점들이 부각되고 있다. 본 종설에서는 전립선영상 판독과 자료체계 2.1 버전의 간단한 개요와 새롭게 부상하는 다음과 같은 문제들에 대해 비판적인 관점에서 논의하고자 한다: mpMRI의 보다 자세한 프로토콜에 대한 필요, 개정된 이행부 판독기준에 대한 검증 부족, 개정된 확산강조영상 및 조영 증강 영상 판독기준, anterior fibromuscular stroma, 중심부 평가, 주변부 신호 및 종양 공격성, 구조화된 판독문 변화에 대한 명료화의 필요, 영상 품질과 수행능력 제어에 대한 필요 및 기타 적응증을 포함하도록 시스템 확장을 위한 적응증.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권9호
• /
• pp.3016-3033
• /
• 2014

The downlink performance of distributed antenna systems (DAS) with antennas selection is investigated in Rayleigh fading multicell environment, and the corresponding system capacity and bit error rate (BER) analysis are presented. Based on the moment generating function, the probability density function (PDF) and cumulative distribution function (CDF) of the effective signal to interference plus noise ratio (SINR) of the system are first derived, respectively. Then, with the available CDF and PDF, the accurate closed-form expressions of average channel capacity and average BER are further derived for exact performance evaluation. To simplify the expression, a simple closed-form approximate expression of average channel capacity is obtained by means of Taylor series expansion, with the performance results close to the accurate expression. Besides, the system outage capacity is analyzed, and an accurate closed-form expression of outage capacity probability is derived. These theoretical expressions can provide good performance evaluation for DAS downlink. It can be shown by simulation that the theoretical analysis and simulation are consistent, and DAS with antenna selection outperforms that with conventional blanket transmission. Moreover, the system performance can be effectively improved as the number of receive antennas increases.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권1호
• /
• pp.1-9
• /
• 2022

In this study, we proposed an image quality control for an automatic exposure control (AEC) of digital radiographic imaging system and tried to analyze the performance of the AEC by various manufacturer. The subjects of the experiment were analyzed for the AEC image quality evaluation using digital radiation generators from four manufacturer such as PHILIPS, GE Healthcare, SAMSUNG Healthcare, DK Medical Solution. We used as materials for the implementation of the image quality evaluation by coins (500 won, KOMSCO, Korea). This study evaluated the performance evaluation of the AEC as image quality and exposure dose (Milliampere-seconds; mAs). The image quality evaluation was tried visual assessment by two radiologic technologists and contrast to noise (CNR) by ImageJ. The exposure dose investigated mAs on digital radiation generators. The radiographic coin images acquired 360 images based on change in the control factors of the AEC, which were kVp, the consistency of field configuration and dominant zone, sensitivity and density. As a result, there was a significant difference in the AEC performance between manufacturer. The CNR by the AEC for each manufacturer showed a difference of up to about 1.9 times. The exposed tube current by the AEC for each manufacturer showed a difference of up to about 5.8 times. It is expected that our proposed evaluation method using coins could be applied as the AEC performance evaluation method in the future.

• Korean Journal of Radiology
• /
• 제23권1호
• /
• pp.139-149
• /
• 2022

Objective: To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists' performance for pulmonary nodule detection on chest radiographs (CXRs). Materials and Methods: A total of 111 adults, including 49 patients with 83 pulmonary nodules, who underwent both CXR using the dual energy technique and chest CT, were enrolled. Using CT as a reference, two independent radiologists evaluated CXR images for the presence or absence of pulmonary nodules in three reading sessions (standard CXR, BSt-DE CXR, and BSp-DL CXR). Person-wise and nodule-wise performances were assessed using receiver-operating characteristic (ROC) and alternative free-response ROC (AFROC) curve analyses, respectively. Subgroup analyses based on nodule size, location, and the presence of overlapping bones were performed. Results: BSt-DE with an area under the AFROC curve (AUAFROC) of 0.996 and 0.976 for readers 1 and 2, respectively, and BSp-DL with AUAFROC of 0.981 and 0.958, respectively, showed better nodule-wise performance than standard CXR (AUAFROC of 0.907 and 0.808, respectively; p ≤ 0.005). In the person-wise analysis, BSp-DL with an area under the ROC curve (AUROC) of 0.984 and 0.931 for readers 1 and 2, respectively, showed better performance than standard CXR (AUROC of 0.915 and 0.798, respectively; p ≤ 0.011) and comparable performance to BSt-DE (AUROC of 0.988 and 0.974; p ≥ 0.064). BSt-DE and BSp-DL were superior to standard CXR for detecting nodules overlapping with bones (p < 0.017) or in the upper/middle lung zone (p < 0.017). BSt-DE was superior (p < 0.017) to BSp-DL in detecting peripheral and sub-centimeter nodules. Conclusion: BSp-DL (GAN-based bone suppression) showed comparable performance to BSt-DE and can improve radiologists' performance in detecting pulmonary nodules on CXRs. Nevertheless, for better delineation of small and peripheral nodules, further technical improvements are required.

• 대한방사선기술학회지:방사선기술과학
• /
• 제35권4호
• /
• pp.309-314
• /
• 2012

Digital Radiography(DR) 시스템은 임상현장에서 아날로그 시스템을 대체하고 널리 이용되고 있다. DR을 이용하여 얻어진 X선 영상의 해상력을 결정짓는 요소에는 이용되는 검출기의 고유 해상력, 피사체의 대조도 및 특성, X선 선질, X선원의 산란, DR 검출기의 성능, X선 변환효율 및 초점의 크기, 피사체의 움직임 등이 있다. DR 검출기를 구성하는 요소에는 X선 포획 요소, 커플링 요소, 정보수집 요소가 있는데 이들은 시스템의 성능에 영향을 미치며, 그 성능은 해상력으로 평가된다. 의료영상 시스템의 해상력은 촬영대상물의 조직 간의 해부학적 영상을 구분하는 능력을 나타낸다. 해상력 평가를 위해 Modulation Transfer Function(MTF)이 보편적으로 이용되고, MTF는 입력 공간주파수 성분에 대한 출력 공간주파수 성분의 비를 나타내는데, 수학적으로 MTF는 Point Spread Function(PSF) 입력에 대한 시스템의 주파수 응답이며 Edge Phantom을 이용한 결과 영상에서 추출된 Line Spread Function(LSF)을 Fourier Transform하면 얻을 수 있다. 일반적으로 임상현장에서 의료영상시스템의 이용 및 관리의 책임은 방사선사가 맡고 있지만, MTF를 측정하기 위해서는 공학적, 수학적 기초 및 C, Fortran, Matlab등의 프로그램 작성 능력이 필요하기 때문에 비 공학도는 정확한 측정이 불가능하다. 의료영상 시스템의 성능 관리 및 최상의 상태를 유지하기 위해 시스템의 성능평가가 이뤄져야 하는데, 이를 위해 본 연구에서는 비공학도가 해상력 성능평가를 할수 있도록 ImageJ 및 Excel을 이용하여 해상력 평가를 할 수 있도록 방법을 제시하고, 제안된 방법을 이용해 계산된 결과와 프로그래밍을 이용해 계산된 결과의 비교를 통해 본 논문에서 제시하는 방법의 유용성을 확인하였다.

• 정보저장시스템학회논문집
• /
• 제9권1호
• /
• pp.17-21
• /
• 2013

Optical coherence tomography (OCT) allows non-invasive, cross-sectional optical imaging of biological tissue with high spatial resolution and acquisition speed. In principle, it is analogous to ultrasound imaging, but uses near-infrared light instead of ultrasound, measuring the time-delay of back-scattered light from within biological tissue. Compared to ultrasound imaging, it exhibits superior spatial resolution (1~10 um) and high sensitivity. Therefore, OCT has been applied to a wide range of applications such as cellular imaging, ophthalmology and cardiology. Here, we describe a novel application of OCT technology in visualizing microneedles embedded in tissue that is developed to deliver drugs into the dermis without the injection mark in the human skin. Detailed three-dimensional structural images of microneedles and biological tissues were obtained. Examining structural modification of microneedles and tissues during insertion process would enable to evaluate performance of various types of microneedles in situ.

• 한국군사과학기술학회지
• /
• 제17권1호
• /
• pp.122-128
• /
• 2014

Remote fourier transform infrared(FTIR) chemical imaging detection system allows detection and identification of gases in the atmosphere from long distances. In this paper, the appropriate field of view(FOV) of the FTIR imaging system was examined and the main performance of the system for the interferometer was described. For the determination of the FOV, simulations of gas dispersion range were performed with the NBC reporting and modeling software(NBC-RAMS) developed by ADD. As a result, minimum 192 mrad of FOV was required for the remote FTIR imaging system to visualize chemical warfare agents dispersed in several hundred meters. At the same time, 0.75 mrad of instantaneous field of view(IFOV) for a linear interferometer proper to take a FOV for the chemical agent imaging.