• Title/Summary/Keyword: Optimal Technique

Search Result 3,174, Processing Time 0.027 seconds

Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis

  • Chenggong Yan;Jie Lin;Haixia Li;Jun Xu;Tianjing Zhang;Hao Chen;Henry C. Woodruff;Guangyao Wu;Siqi Zhang;Yikai Xu;Philippe Lambin
    • Korean Journal of Radiology
    • /
    • v.22 no.6
    • /
    • pp.983-993
    • /
    • 2021
  • Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

Development of a Probabilistic Approach to Predict Motion Characteristics of a Ship under Wind Loads (풍하중을 고려한 확률론적 운동특성 평가기법 개발에 관한 연구)

  • Sang-Eui Lee
    • Journal of Navigation and Port Research
    • /
    • v.47 no.6
    • /
    • pp.315-323
    • /
    • 2023
  • Marine accidents due to loss of stability of small ships have continued to increase over the past decade. In particular, since sudden winds have been pointed out as main causes of most small ship accidents, safety measures have been established to prevent them. In this regard, to prevent accidents caused by sudden winds, a systematic analysis technique is required. The aim of the present study was to develop a probabilistic approach to estimate extreme value and evaluate effects of wind on motion characteristics of ships. The present study included studies of motion analysis, extraction of extreme values, and motion characteristics. A series analysis was conducted for three conditions: wave only, wave with uniform wind speed, and wave with the NPD wind model. Hysteresis filtering and Peak-Valley filtering techniques were applied to time-domain motion analysis results for extreme value extraction. Using extracted extreme values, the goodness of fit test was performed on four distribution functions to select the optimal distribution-function that best expressed extreme values. Motion characteristics of a fishing boat were evaluated for three periodic motion conditions (Heave, Roll, and Pitch) and results were compared. Numerical analysis was performed using a commercial solver, ANSYS-AQWA.

AutoML Machine Learning-Based for Detecting Qshing Attacks Malicious URL Classification Technology Research and Service Implementation (큐싱 공격 탐지를 위한 AutoML 머신러닝 기반 악성 URL 분류 기술 연구 및 서비스 구현)

  • Dong-Young Kim;Gi-Seong Hwang
    • Smart Media Journal
    • /
    • v.13 no.6
    • /
    • pp.9-15
    • /
    • 2024
  • In recent trends, there has been an increase in 'Qshing' attacks, a hybrid form of phishing that exploits fake QR (Quick Response) codes impersonating government agencies to steal personal and financial information. Particularly, this attack method is characterized by its stealthiness, as victims can be redirected to phishing pages or led to download malicious software simply by scanning a QR code, making it difficult for them to realize they have been targeted. In this paper, we have developed a classification technique utilizing machine learning algorithms to identify the maliciousness of URLs embedded in QR codes, and we have explored ways to integrate this with existing QR code readers. To this end, we constructed a dataset from 128,587 malicious URLs and 428,102 benign URLs, extracting 35 different features such as protocol and parameters, and used AutoML to identify the optimal algorithm and hyperparameters, achieving an accuracy of approximately 87.37%. Following this, we designed the integration of the trained classification model with existing QR code readers to implement a service capable of countering Qshing attacks. In conclusion, our findings confirm that deriving an optimized algorithm for classifying malicious URLs in QR codes and integrating it with existing QR code readers presents a viable solution to combat Qshing attacks.

Radiologic assessment of the optimal point for tube thoracostomy using the sternum as a landmark: a computed tomography-based analysis

  • Jaeik Jang;Jae-Hyug Woo;Mina Lee;Woo Sung Choi;Yong Su Lim;Jin Seong Cho;Jae Ho Jang;Jea Yeon Choi;Sung Youl Hyun
    • Journal of Trauma and Injury
    • /
    • v.37 no.1
    • /
    • pp.37-47
    • /
    • 2024
  • Purpose: This study aimed at developing a novel tube thoracostomy technique using the sternum, a fixed anatomical structure, as an indicator to reduce the possibility of incorrect chest tube positioning and complications in patients with chest trauma. Methods: This retrospective study analyzed the data of 184 patients with chest trauma who were aged ≥18 years, visited a single regional trauma center in Korea between April and June 2022, and underwent chest computed tomography (CT) with their arms down. The conventional gold standard, 5th intercostal space (ICS) method, was compared to the lower 1/2, 1/3, and 1/4 of the sternum method by analyzing CT images. Results: When virtual tube thoracostomy routes were drawn at the mid-axillary line at the 5th ICS level, 150 patients (81.5%) on the right side and 179 patients (97.3%) on the left did not pass the diaphragm. However, at the lower 1/2 of the sternum level, 171 patients (92.9%, P<0.001) on the right and 182 patients (98.9%, P= 0.250) on the left did not pass the diaphragm. At the 5th ICS level, 129 patients (70.1%) on the right and 156 patients (84.8%) on the left were located in the safety zone and did not pass the diaphragm. Alternatively, at the lower 1/2, 1/3, and 1/4 of the sternum level, 139 (75.5%, P=0.185), 49 (26.6%, P<0.001), and 10 (5.4%, P<0.001), respectively, on the right, and 146 (79.3%, P=0.041), 69 (37.5%, P<0.001), and 16 (8.7%, P<0.001) on the left were located in the safety zone and did not pass the diaphragm. Compared to the conventional 5th ICS method, the sternum 1/2 method had a safety zone prediction sensitivity of 90.0% to 90.7%, and 97.3% to 100% sensitivity for not passing the diaphragm. Conclusions: Using the sternum length as a tube thoracostomy indicator might be feasible.

Comparative Study of Fish Detection and Classification Performance Using the YOLOv8-Seg Model (YOLOv8-Seg 모델을 이용한 어류 탐지 및 분류 성능 비교연구)

  • Sang-Yeup Jin;Heung-Bae Choi;Myeong-Soo Han;Hyo-tae Lee;Young-Tae Son
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.30 no.2
    • /
    • pp.147-156
    • /
    • 2024
  • The sustainable management and enhancement of marine resources are becoming increasingly important issues worldwide. This study was conducted in response to these challenges, focusing on the development and performance comparison of fish detection and classification models as part of a deep learning-based technique for assessing the effectiveness of marine resource enhancement projects initiated by the Korea Fisheries Resources Agency. The aim was to select the optimal model by training various sizes of YOLOv8-Seg models on a fish image dataset and comparing each performance metric. The dataset used for model construction consisted of 36,749 images and label files of 12 different species of fish, with data diversity enhanced through the application of augmentation techniques during training. When training and validating five different YOLOv8-Seg models under identical conditions, the medium-sized YOLOv8m-Seg model showed high learning efficiency and excellent detection and classification performance, with the shortest training time of 13 h and 12 min, an of 0.933, and an inference speed of 9.6 ms. Considering the balance between each performance metric, this was deemed the most efficient model for meeting real-time processing requirements. The use of such real-time fish detection and classification models could enable effective surveys of marine resource enhancement projects, suggesting the need for ongoing performance improvements and further research.

Risk assessment for development of consecutive shield TBM technology (연속굴착형 쉴드 TBM 기술 개발을 위한 리스크 평가)

  • Kibeom Kwon;Hangseok Choi;Chaemin Hwang;Sangyeong Park;Byeonghyun Hwang
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.26 no.4
    • /
    • pp.303-314
    • /
    • 2024
  • Recently, the consecutive shield tunnel boring machine (TBM) has gained attention for its potential to enhance TBM penetration rates. However, its development requires a thorough risk assessment due to the unconventional nature of its equipment and hydraulic systems, coupled with the absence of design or construction precedents. This study investigated the causal relationships between four accidents and eight relevant sources associated with the consecutive shield TBM. Subsequently, risk levels were determined based on expert surveys and a risk matrix technique. The findings highlighted significant impacts associated with collapses or surface settlements and the likelihood of causal combinations leading to misalignment. Specifically, this study emphasized the importance of proactive mitigation measures to address collapses or surface settlements caused by inadequate continuous tail void backfill or damaged thrust jacks. Furthermore, it is recommended to develop advanced non-destructive testing technology capable of comprehensive range detection across helical segments, to design a sequential thrust jack propulsion system, and to determine an optimal pedestal angle.

Evidence of Cortical Reorganization in a Monoparetic Patient with Cerebral Palsy Detected by Combined Functional MRI and TMS

  • Kwon, Yong-Hyun;Jang, Sung-Ho;Lee, Mi-Young;Byun, Woo-Mok;Cho, Yoon-Woo;Ahn, Sang-Ho
    • Journal of Yeungnam Medical Science
    • /
    • v.22 no.1
    • /
    • pp.96-103
    • /
    • 2005
  • The motor recovery mechanism of a 21-year-old male monoparetic patient with cerebral palsy, who had complained of a mild weakness on his right hand since infancy, was examined using functional Magnetic Resonance Imaging (fMRI) and Transcranial Magnetic Stimulation (TMS). The patient showed mild motor impairment on the right hand. MRI located the main lesion on the left precentral knob of the brain. fMRI was performed on this patient as well as 8 control subjects using the Blood Oxygen Level Dependent technique at 1.5 T with a standard head coil. The motor activation task consisted of finger flexionextension exercises at 1 Hz cycles. TMS was carried out using a round coil. The anterior portion of the coil was applied tangentially to the scalp at a 1.0 cm separation. Magnetic stimulation was carried out with the maximal output. The Motor Evoked Potentials (MEPs) from both Abductor Pollicis Brevis muscles (APB) were obtained simultaneously. fMRI revealed that the unaffected (right) primary sensori-motor cortex (SM1), which was centered on precentral knob, was activated by the hand movements of the control subjects as well as by the unaffected (left) hand movements of the patient. However, the affected(right) hand movements of the patient activated the medial portion of the injured precentral knob of the left SM1. The optimal scalp site for the affected (right) APB was located at 1 cm medial to that of the unaffected (left) APB. When the optimal scalp site was stimulated, the MEP characteristics from the affected (right) APB showed a delayed latency, lower amplitude, and a distorted figure compared with that of the unaffected (left) APB. Therefore, the motor function of the affected (right) hand was shown to be reorganized in the medial portion of the injured precentral knob.

  • PDF

Optimal Water Allocation by Dynamic Programming (동적계획법에 의한 물 배분)

  • 이순탁;이진우
    • Water for future
    • /
    • v.18 no.2
    • /
    • pp.163-174
    • /
    • 1985
  • This study aims at the development of a technique for the optimal water allocation by applying Dynamic Programming Model for the effective usage and rational allocation of water resources, in case of which limited water resources in river basin should be used in several stages. In analytical procedure the possible allocable area was firstly zoned into the four areas: Pohang area ($C_1$), Yeungcheon area ($C_2$), Gyeungsan area ($C_3$), Daegu area ($C_4$), which are located between the Yeongcheon dam and the confluence of the lower Kumho river and the main course of the Nakdong river. Secondly, a return function was determined on the basis of the correlation between the GRP in each area and the amount of water used to it. A DP Model, finally, was applied to the allocation of the water resources according to both their usage and the areas. As a result, the fact has been found that when allocating by the area, $C_1$ could be possibly supplied only with the water resources avaiable from the Yeungchon dam, and the maximum units supplied to $C_1$ should be 240 units ($1unit=10^3㎥$ per day), beyond which we ought to develop an alternative water resources. Also, the return from the allocation by the usage exceeded the one from it by the area. At the same time it was more profitable to limit the water supply to $C_1$ into 217 units. In the allocation by the area 240 units and 80 units, if only the water resources available from the Yeungcheon dam used, and 360 units and 80 units if the Doil dam used additionally, could be supplied to $C_1$ and the lower region respectively. In the allocation by the usage 103 units for industrial water with 33 units for both domestic and commercial water and 183 units, if only the water resources available from the Yeungcheon dam used, and 103 units with 33 units and 304 units, if the Doil dam taken into consideration additionally, could be supplied to $C_1$ and the lower region respectively. Therefore, much more water could be allocated to the region of lower Kumho river if the method of water allocation by the usage.

  • PDF

Computer Simulations of Hoffman Brain Phantom:Sensitivity Measurements and Optimization of Data Analysis of 〔Tc-99m〕ECD SPECT Before and After Acftazolamide Administraton (Acetazolamide 사용전후 〔Tc-99m〕 EDC SPECT 데이타 분석 방법의 최적화 및 민감도 측정)

  • Kim, Hee-Joung;Lee, Hee-Kyung
    • Progress in Medical Physics
    • /
    • v.6 no.2
    • /
    • pp.71-81
    • /
    • 1995
  • Consecutive brain 〔Tc-99m〕ECD SPECT studies before and after acetazolamide (Diamox) administration have been performed with patients for the evaluation of cerebrovascular hemodynamic reserve. However, the quantitaitve potential of SPECT Diamox imaging is limited as a result of degrading fractors such as finite detector resolution, attenuation, scatter, poor counting statistics, and methods of data analysis. Making physical measurements in phantoms filled with known amounts of radioactivity can help characterize and potentially quantify the sensitivities. However, it is often very difficult to make a realistic phantom simulating patients in clinical situations. By computer simulation, we studied the sensitivities of ECD SPECT before and after Diamox administration. The sensitivity is defined as ($\Delta$N/N)/($\Delta$S/S)$\times$100%, where $\Delta$N denotes the differences in mean counts between post-and pre-Diamox in the measured data, N denotes the mean counts before Diamox in the measure data, $\Delta$S denotes the differences in mean counts between post-and pre-Diamox in the model, and S denotes the mean counts before Diamox in the model. In clinical Diamox studies, the percentage changes of radioactivity could be determined to measure changes in radioactivity concentration by Diamox after subtracting pre-from post-Diamox data. However, the optimal amount of subtraction for 100% sensitivity is not known since this requires a thorough sensitivity analysis by computer simulation. For consecutive brain SPECT imaging model before and after Diamox, when 30% increased radioactivity concentrations were assingned for Diamox effect in model, the sensitivities were measured as 51.03, 73.4, 94.00, 130.74% for 0, 100, 150, 200% subtraction, respectively. Sensitivity analysis indicated that the partial voluming effects due to finite detector resolution and statistical noise result in a significant underestimation of radioactivity measurements and the amount of underestimation depends on the. % increase of radioactivity concentration and % subtraction of pre-from post-Diamox data. The 150% subtraction appears to be optimal in clinical situations where we expect approximately 30% changes in radioactivity concentration. The computer simulation may be a powerful technique to study sensitivities of ECD SPECT before and after Diamox administration.

  • PDF

Study on an Effective Decellularization Technique for Cardiac Valve, Arterial Wall and Pericardium Xenographs: Optimization of Decellularization (이종 심장 판막 및 대혈관 이식편과 심낭에서 효과적인 탈세포화 방법에 관한 연구: 탈세포화의 최적화)

  • Park, Chun-Soo;Kim, Yong-Jin;Sung, Si-Chan;Park, Ji-Eun;Choi, Sun-Young;Kim, Woong-Han;Kim, Kyung-Hwan
    • Journal of Chest Surgery
    • /
    • v.41 no.5
    • /
    • pp.550-562
    • /
    • 2008
  • Background: We attempted to reproduce a previously reported method that is known to be effective for decellularization, and we sought to find the optimal condition for decellularization by introducing some modifications to this method. Material and Method: Porcine semilunar valves, arterial walls and pericardium were processed for decellularization with using a variety of combinations and concentrations of decellularizing agents under different conditions of temperature, osmolarity and incubation time. The degree of decellularization and the preservation of the extracellular matrix were evaluated by staining with hematoxylin and eosin and with alpha-Gal and DAPI in some of the decellularized tissues. Result: Decellularization was achieved in the specimens that were treated with sodium deoxycholate, sodium dodesyl sulfate, Triton X-100 and sodium dodesyl sulfate with Triton X-100 as single-step methods, and this was also achieved in the specimens that were treated with hypotonic solution ${\rightarrow}$ Triton X-100 ${\rightarrow}$ sodium dodesyl sulfate, sodium deoxycholate ${\rightarrow}$ hypotonic solution ${\rightarrow}$ sodium dodesyl sulfate, and hypotonic solution sodium dodesyl sulfate as multi-step methods. Conclusion: Considering the number and the amount of the chemicals that were used, the incubation time and the degree of damage to the extracellular matrix, a single-step method with sodium dodesyl sulfate and Triton X-100 and a multi-step method with hypotonic solution followed by sodium dodesyl sulfate were both relatively optimal methods for decellularization in this study.