• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.6
• /
• pp.3735-3742
• /
• 2013

Background: Cardamom (Elettaria cardamom), also known as "Queen of Spices", has been traditionally used as a culinary ingredient due to its pleasant aroma and taste. In addition to this role, studies on cardamom have demonstrated cancer chemopreventive potential in in vitro and in vivo systems. Nevertheless, the precise poly-pharmacological nature of naturally occurring chemo-preventive compounds in cardamom has still not been fully demystified. Methods:In this study, an effort has been made to identify the proapoptopic, anti-inflammatory, anti-proliferative, anti-invasive and anti-angiogenic targets of Cardamom's bioactive principles (eucalyptol, alpha-pinene, beta-pinene, d-limonene and geraniol) by employing a dual reverse virtual screening protocol. Experimentally proven target information of the bioactive principles was annotated from bioassay databases and compared with the virtually screened set of targets to evaluate the reliability of the computational identification. To study the molecular interaction pattern of the anti-tumor action, molecular docking simulation was performed with Auto Dock Pyrx. Interaction studies of binding pose of eucalyptol with Caspase 3 were conducted to obtain an insight into the interacting amino acids and their inter-molecular bondings. Results:A prioritized list of target proteins associated with multiple forms of cancer and ranked by their Fit Score (Pharm Mapper) and descending 3D score (Reverse Screen 3D) were obtained from the two independent inverse screening platforms. Molecular docking studies exploring the bioactive principle targeted action revealed that H- bonds and electrostatic interactions forms the chief contributing factor in inter-molecular interactions associated with anti-tumor activity. Eucalyptol binds to the Caspase 3 with a specific framework that is well-suited for nucleophilic attacks by polar residues inside the Caspase 3 catalytic site. Conclusion:This study revealed vital information about the poly-pharmacological anti-tumor mode-of-action of essential oils in cardamom. In addition, a probabilistic set of anti-tumor targets for cardamom was generated, which can be further confirmed by in vivo and in vitro experiments.

• Nuclear Engineering and Technology
• /
• v.44 no.1
• /
• pp.53-60
• /
• 2012

The aim of this study was to explore the spatial and energy resolutions of a PET scanner that we have recently developed. The scanner, which consists of six detector modules with 1-layer LGSO crystals, has a hexagonal configuration with a faceto- face distance of 86.4 mm between two opposite PET modules; such properties facilitate the imaging of small animals. A $^{22}Na$ point source was employed to estimate horizontal and vertical spatial resolutions. To assess the energy resolution, a uniform $^{18}F$ cylindrical phantom was scanned. A software-based spectrum analysis of list-mode data was used to assign a local energy window centered on the photopeak position for every single crystal. For the image reconstruction, an ML-EM algorithm was used. The spatial resolutions at the center of the scanner were 0.99 mm in the horizontal direction and 1.13 mm in the vertical direction. The energy resolution averaged over each PMT ranged from 13.3%-14.3%, which gave an average value of 13.8%. These results show that this simple system is promising for small animal imaging with excellent spatial and energy resolutions.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.21 no.2
• /
• pp.65-73
• /
• 2017

Purpose 3D 프린팅 기술은 3D 스캔이나 모델링을 통하여 적측가공 방식으로 제작하는 기공기술로서 금형 없이 직접 생산이 가능하고 빠른 시간 내에 제작이 가능하여 최근 다양한 산업분야에서 본격적으로 적용되고 있다. 3D 프린팅 기술은 의료분야에 있어, 영상의학 및 방사선 치료분야에서 다양하게 활용되고 있지만 핵의학 분야에서는 관련 연구가 미비한 실정이다. 그러므로 본 연구는 기존에 적용되고 있는 핵의학분야 팬텀과 3D 프린팅 기술로 제작된 텀의 특성을 비교하고 적용 가능성을 평가하는데 목적을 두었다. Materials and Methods 방사선 투과도 변화측정 국제기준 팬텀인 알루미늄(Aluminum) 계단 쐐기(step wedge)를 기준($140mm{\times}62mm{\times}35mm$)으로 PMMA(Poly Methyl Meta Acrylate)와 ABS(Acrylonitrile Butadiene Styrene)재질로 각각 동일한 크기의 팬텀을 제작하였다. PMMA 팬텀은 핵의학 분야에서 주로 적용되는 팬텀의 성분과 동일한 소재로 제작하였고, ABS 팬텀 제작은 3D 프린팅 기술의 액체 기반형의 SLA(Stereo Lithography Apparatus)기법을 사용하여 제작하였다. 본 연구는 SPECT/CT장비 BrightView XCT(Philips Health Care, Cleveland, USA)를 이용하였다. 영상 획득은 Rectangular Flood phantom(Biodex, New York, USA) $^{99m}TcO_4$ 3, 6 mCi와 $^{57}Co$ lood phantom(adqual, New Hampshire, USA) $^{57}Co$ 20 mCi를 이용하여 Aluminum, PMMA, ABS 팬텀에 대해 60 min 리스트모드(List mode)로 획득하였다. 획득한 영상의 분석을 위해 관심영역(ROI)을 설정하여 각 팬텀의 단계별로 평가하였다. Results 방사선원의 종류 및 방사선량에 따라 ABS 팬텀의 계수치는 PMMA 팬텀의 계수치와 유사한 값을 나타내며, 두께의 증가에 따라 선형적으로 감소하였다. Aluminum, PMMA, ABS 팬텀의 선감약계수를 비교했을 때, Aluminum 팬텀의 선감약계수는 나머지 두 팬텀보다 수치가 높았고, PMMA, ABS 팬텀에서는 근사치의 선감약계수가 나타났다. Conclusion 3D 프린팅 기술로 제작된 ABS 팬텀을 기준으로 PMMA 팬텀은 두께가 증가함에 따른 계수치의 변화가 유사하게 선형적으로 감소하였고, 선감약계수도 근사치로 나타내었다. ABS 팬텀의 핵의학적 적용 가능성을 확인할 수 있었으며, 추후 연구를 통해 세부적인 교정치(correction value)를 적용한다면 활발한 적용이 가능하리라 사료된다.

• Asia pacific journal of information systems
• /
• v.22 no.4
• /
• pp.31-49
• /
• 2012

In this essay, we problematize the problematics of the KMIS SOLOMO research agenda. We propose that the SOLOMO agenda is a conditioned product of the various assumptions, biases, premises, and presuppositions that the field of IS collectively succumbs to and shares, and thus needs to be problematized to arrive at a new set of research questions for the field. The problematization begins with the ontology that underlies the agenda. We argue that the agenda is largely drawn from a dichotomic, deep ontology of Human vs. Technology. While such ontology is neither right nor wrong in its own right, we suggest it is what underlies and influences the field's whole mode of inquiry including its research agenda. We propose an alternative ontology, the Actor-Network Theory (ANT), which as a flat ontology provides a radically different set of research questions for the field. Next we take issue with the teleology of the SOLOMO agenda, and suggest that the telos of the agenda, and of the field of IS and the whole of Management discipline together, are anchored upon the capitalist episteme so that it creates a significant hole in its teleological scape. While not in any sense calling for an ideological demagogue, we propose that the field of IS should open itself to an alternative teleology including a leftist perspective. We draw upon the Critical Management Studies (CMS) to explore how further problematization can be made on the SOLOMO agenda, generating questions about its performativity, denaturalization, and reflexivity. As a result of the discussions, a list of new problematized research questions for the SOLOMO agenda is generated. In the end we state the motivation of the essay and call for a critical refurbishing of the field of IS.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.849-858
• /
• 2004

Most of supervised teaming algorithms could be applied after that continuous variables are transformed to categorical ones at the preprocessing stage in order to avoid the difficulty of processing continuous variables. This preprocessing stage is called global discretization, uses the class distribution list called bins. But, when data are large and the range of the variable to be discretized is very large, many sorting and merging should be performed to produce a single bin because most of global discretization methods need a single bin. Also, if new data are added, they have to perform discretization from scratch to construct categories influenced by the data because the existing methods perform discretization in batch mode. This paper proposes a method that extracts sample points and performs discretization from these sample points in order to solve these problems. Because the approach in this paper does not require merging for producing a single bin, it is efficient when large data are needed to be discretized. In this study, an experiment using real and synthetic datasets was made to compare the proposed method with an existing one.

• Nuclear Engineering and Technology
• /
• v.51 no.5
• /
• pp.1417-1427
• /
• 2019

In this study, we evaluated the performance of a commercial pixelated cadmium zinc telluride (CZT) detector for spectroscopy and identified its feasibility as a Compton camera for radiation monitoring in a nuclear power plant. The detection system consisted of a $20mm{\times}20mm{\times}5mm$ CZT crystal with $8{\times}8$ pixelated anodes and a common cathode, in addition to an application specific integrated circuit. The performance of the various radioisotopes $^{57}Co$, $^{133}Ba$, $^{22}Na$, and $^{137}Cs$ was evaluated. In general, the amplitude of the induced signal in a CZT crystal depends on the interaction position and material non-uniformity. To minimize this dependency, a drift time correction was applied. The depth of each interaction was calculated by the drift time and the positional dependency of the signal amplitude was corrected based on the depth information. After the correction, the Compton regions of each spectrum were reduced, and energy resolutions of 122 keV, 356 keV, 511 keV, and 662 keV peaks were improved from 13.59%, 9.56%, 6.08%, and 5%-4.61%, 2.94%, 2.08%, and 2.2%, respectively. For the Compton imaging, simulations and experiments using one $^{137}Cs$ source with various angular positions and two $^{137}Cs$ sources were performed. Individual and multiple sources of $^{133}Ba$, $^{22}Na$, and $^{137}Cs$ were also measured. The images were successfully reconstructed by weighted list-mode maximum likelihood expectation maximization method. The angular resolutions and intrinsic efficiency of the $^{137}Cs$ experiments were approximately $7^{\circ}-9^{\circ}$ and $5{\times}10^{-4}-7{\times}10^{-4}$, respectively. The distortions of the source distribution were proportional to the offset angle.

• Journal of radiological science and technology
• /
• v.44 no.4
• /
• pp.343-350
• /
• 2021

3D printing technology is an additive manufacturing technology produced through 3D scanning or modeling method. This technology can be produced in a short time without mold, which has recently been applied in earnest in various fields. In the medical field, 3D printing technology is used in various fields of radiology and radiation therapy, but related research is insufficient in the field of nuclear medicine. In this study, we compare the characteristics of traditional nuclear medicine phantom with 3D printing technology and evaluate its applicability in clinical trials. We manufactured the same size phantom of poly methyl meta acrylate(PMMA) and acrylonitrile butadiene styrene(ABS) based on the aluminum step wedge. We used BrightView XCT(Philips Health Care, Cleveland, USA) SPECT/CT. We acquired 60 min list mode for Aluminum, PMMA and ABS phantoms using Rectangular Flood Phantom (Biodex, New York, USA) ^99mTcO₄ 3 mCi(111 MBq), 6 mCi (222MBq) and ⁵⁷Co Flood phantom(adq, New Hampshire, USA). For the analysis of acquired images, the region of interest(ROI) were drawn and evaluated step by step for each phantom. Depending on the type of radioisotope and radiation dose, the counts of the ABS phantom was similar to that of the PMMA phantom. And as the step thickness increased, the counts decreased linearly. When comparing the linear attenuation coefficient of Aluminum, PMMA and ABS phantom, the linear attenuation coefficient of the aluminium phantom was higher than that of the others, and the PMMA and ABS phantom had similar the linear attenuation coefficient. Based on ABS phantom manufactured by 3D printing technology, as the thickness of the PMMA phantom increased, the counts and linear attenuation coefficient decreased linearly. It has been confirmed that ABS phantom is applicable in the clinical field of nuclear medicine. If the calibration factor is applied through further research, it is believed that practical application will be possible.

• Journal of radiological science and technology
• /
• v.44 no.6
• /
• pp.655-661
• /
• 2021

Positron emission tomography (PET) images is affected by acquisition time, short acquisition times results in low gamma counts leading to degradation of image quality by statistical noise. Noise2Void(N2V) is self supervised denoising model that is convolutional neural network (CNN) based deep learning. The purpose of this study is to evaluate denoising performance of N2V for PET image with a short acquisition time. The phantom was scanned as a list mode for 10 min using Biograph mCT40 of PET/CT (Siemens Healthcare, Erlangen, Germany). We compared PET images using NEMA image-quality phantom for standard acquisition time (10 min), short acquisition time (2min) and simulated PET image (S2 min). To evaluate performance of N2V, the peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE), structural similarity index (SSIM) and radio-activity recovery coefficient (RC) were used. The PSNR, NRMSE and SSIM for 2 min and S2 min PET images compared to 10min PET image were 30.983, 33.936, 9.954, 7.609 and 0.916, 0.934 respectively. The RC for spheres with S2 min PET image also met European Association of Nuclear Medicine Research Ltd. (EARL) FDG PET accreditation program. We confirmed generated S2 min PET image from N2V deep learning showed improvement results compared to 2 min PET image and The PET images on visual analysis were also comparable between 10 min and S2 min PET images. In conclusion, noisy PET image by means of short acquisition time using N2V denoising network model can be improved image quality without underestimation of radioactivity.

• Journal of radiological science and technology
• /
• v.45 no.3
• /
• pp.225-232
• /
• 2022

Fine dust threatens human health in various forms, depending on the particle size, such as by causing respiratory, cardiovascular, and brain diseases, after entering the body via the lungs. The aim of this study was to correlate fine dust exposure with changes in brain blood flow in Sprague Dawley rats by using micro-positron emission tomography and elucidate the possibility of developing cerebrovascular diseases caused by fine dust. The subjects were exposured to an average fine dust (particulate matter 2.5) of 206.2 ± 7.74 to ten rats four times a day, twice a day for 90 min. Before the experiment, they were maintained at NPO to the maximize the intake of ¹⁸F-fluorodeoxy glucose(¹⁸F-FDG) and minimize changes in the ¹⁸F-FDG biomass depending on the ambient environment and body temperature of the rats. PET images were acquired in the list mode 40 min after injecting ¹⁸F-FDG 44.4 MBq into the rats tail vein using a micro-PET scanner pre and post exposure to fine dust. We found that the whole brain level of ¹⁸F-FDG standardized uptake value in rats averaged 5.21 ± 0.52 g/mL pre and 4.22 ± 0.48 g/mL post exposure to fine dust, resulting in a statistically significant difference. Fine dust was able to alter brain activity after entering the body via the lungs in various forms depending on the particle size.