• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.343-350
• /
• 2024

Since the release of Meta's Segment Anything Model (SAM), a large-scale vision transformer generation model with rapid image segmentation capabilities, several studies have been conducted to apply this technology in various fields. In this study, we aimed to investigate the applicability of SAM for water bodies detection and extraction using the QGIS Geo-SAM plugin, which enables the use of SAM with satellite imagery. The experimental data consisted of Compact Advanced Satellite 500 (CAS500)-1 images. The results obtained by applying SAM to these data were compared with manually digitized water objects, Open Street Map (OSM), and water body data from the National Geographic Information Institute (NGII)-based hydrological digital map. The mean Intersection over Union (mIoU) calculated for all features extracted using SAM and these three-comparison data were 0.7490, 0.5905, and 0.4921, respectively. For features commonly appeared or extracted in all datasets, the results were 0.9189, 0.8779, and 0.7715, respectively. Based on analysis of the spatial consistency between SAM results and other comparison data, SAM showed limitations in detecting small-scale or poorly defined streams but provided meaningful segmentation results for water body classification.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.69-79
• /
• 2024

Field geotechnical data are obtained from various field and laboratory tests and are documented in geotechnical investigation reports. For efficient design and construction, digitizing these geotechnical parameters is essential. However, current practices involve manual data entry, which is time-consuming, labor-intensive, and prone to errors. Thus, this study proposes an automatic data extraction method from geotechnical investigation reports using image-based deep learning models and text-mining techniques. A deep-learning-based page classification model and a text-searching algorithm were employed to classify geotechnical investigation report pages with 100% accuracy. Computer vision algorithms were utilized to identify valid data regions within report pages, and text analysis was used to match and extract the corresponding geotechnical data. The proposed model was validated using a dataset of 205 geotechnical investigation reports, achieving an average data extraction accuracy of 93.0%. Finally, a user-interface-based program was developed to enhance the practical application of the extraction model. It allowed users to upload PDF files of geotechnical investigation reports, automatically analyze these reports, and extract and edit data. This approach is expected to improve the efficiency and accuracy of digitizing geotechnical investigation reports and building geotechnical databases.

• Investigative Magnetic Resonance Imaging
• /
• v.8 no.1
• /
• pp.42-49
• /
• 2004

Purpose : The quantization noise in magnetic resonance imaging (MRI) systems is analyzed. The signal-to-quantization noise ratio (SQNR) in the reconstructed image is derived from the level of quantization in the signal in spatial frequency domain. Based on the derived formula, the SQNRs in various main magnetic fields with different receiver systems are evaluated. From the evaluation, the quantization noise could be a major noise source determining overall system signal-to-noise ratio (SNR) in high field MRI system. A few methods to reduce the quantization noise are suggested. Materials and methods : In Fourier imaging methods, spin density distribution is encoded by phase and frequency encoding gradients in such a way that it becomes a distribution in the spatial frequency domain. Thus the quantization noise in the spatial frequency domain is expressed in terms of the SQNR in the reconstructed image. The validity of the derived formula is confirmed by experiments and computer simulation. Results : Using the derived formula, the SQNRs in various main magnetic fields with various receiver systems are evaluated. Since the quantization noise is proportional to the signal amplitude, yet it cannot be reduced by simple signal averaging, it could be a serious problem in high field imaging. In many receiver systems employing analog-to-digital converters (ADC) of 16 bits/sample, the quantization noise could be a major noise source limiting overall system SNR, especially in a high field imaging. Conclusion : The field strength of MRI system keeps going higher for functional imaging and spectroscopy. In high field MRI system, signal amplitude becomes larger with more susceptibility effect and wider spectral separation. Since the quantization noise is proportional to the signal amplitude, if the conversion bits of the ADCs in the receiver system are not large enough, the increase of signal amplitude may not be fully utilized for the SNR enhancement due to the increase of the quantization noise. Evaluation of the SQNR for various systems using the formula shows that the quantization noise could be a major noise source limiting overall system SNR, especially in three dimensional imaging in a high field imaging. Oversampling and off-center sampling would be an alternative solution to reduce the quantization noise without replacement of the receiver system.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.6
• /
• pp.355-363
• /
• 2003

Purpose: Regional contractility can be calculated using the regional volume change of left ventricle measured by gated myocardial SPECT image and curve of central artery pressure obtained from radial artery pressure data. In this study, a program to obtain the regional contractility was developed, and reproducibility of regional contractility measurement was assessed. Materials and Methods: Seven patients(male:female=5:2, $58{\pm}11.9$ years) with coronary artery diseases underwent gated Tc-99m MIBI myocardial SPECT twice without delay between two scans. Regional volume change of left ventricle was estimated using CSA (Cardiac SPECT Analyzer) software developed in this study. Regional contractility was iteratively estimated from the time-elastance curve obtained using the time-pressure curve and regional time-volume curve. Reproducibility of regional contractility measurement assessed by comparing the contractility values measured twice from the same SPECT data and by comparing those measured from the pair of SPECT data obtained from a same patient. Results: Measured regional contractility was $3.36{\pm}3.38{mm}Hg/mL$ using 15-segment model, $3.16{\pm}2.25{mm}Hg/mL$ using 7-segment model, and $3.11{\pm}2.57{mm}Hg/mL$ using 5-segment model. The harmonic average of regional contractility value was almost identical to the global contractility. Correlation coefficient of regional contractility values measured twice from the same data was greater than 0.97 for all models, and two standard deviations of contractility difference on Bland Altman plot were 1.5%, 1.0%, and 0.9% for 15-, 7-, and 5-segment models, respectively. Correlation coefficient of regional contractility values measured from the pair of SPECT data obtained from a same patient was greater than 0.95 for all models, and two standard deviations on Bland Altman plot were 2.2%, 1.0%, and 1.2%. Conclusion: Regional contractility of left ventricle measured using developed software in this study was reproducible. Regional contractility of left ventricle will be a new useful index for myocardial function after analysis of the clinical data.

• The Korean Journal of Nuclear Medicine
• /
• v.35 no.2
• /
• pp.89-99
• /
• 2001

Purpose: In this study, we developed a new software tool for the analysis of renal scintigraphy which can be modified more easily by a user who needs to study new clinical applications, and the appropriateness of the results from our program was studied. Materials and Methods: The analysis tool was programmed with IDL5.2 and designed for use on a personal computer running Windows. For testing the developed tool and studying the appropriateness of the calculated glomerular filtration rate (GFR), $^{99m}Tc$-DTPA was administered to 10 adults in normal condition. In order to study the appropriateness of the calculated mean transit time (MTT), $^{99m}Tc-DTPA\;and\;^{99m}Tc-MAG3$ were administered to 11 adults in normal condition and 22 kidneys were analyzed. All the images were acquired with ORBITOR. the Siemens gamma camera. Results: With the developed tool, we could show dynamic renal images and time activity curve (TAC) in each ROI and calculate clinical parameters of renal function. The results calculated by the developed tool were not different statistically from the results obtained by the Siemens application program (Tmax: p=0.68, Relative Renal Function: p:1.0, GFR: p=0.25) and the developed program proved reasonable. The MTT calculation tool proved to be reasonable by the evaluation of the influence of hydration status on MTT. Conclusion: We have obtained reasonable clinical parameters for the evaluation of renal function with the software tool developed in this study. The developed tool could prove more practical than conventional, commercial programs.

• The Korean Journal of Nuclear Medicine
• /
• v.31 no.1
• /
• pp.19-29
• /
• 1997

Recently, [I-123]IPT SPECT has been used for early diagnosis of Parkinson's patients(PP) by imaging dopamine transporters. The dynamic time activity curves in basal ganglia(BG) and occipital cortex(OCC) without blood samples were obtained for 2 hours. These data were then used to measure dopamine transporters by operationally defined ratio methods of (BG-OCC)/OCC at 2 hrs, binding potential $R_v=k_3/k_4$ using graphic method or $R_A$= (ABBG-ABOCC)/ABOCC for 2 hrs, where ABBG represents accumulated binding activity in basal ganglia(${\int}^{120min}_0$ BG(t)dt) and ABOCC represents accumulated binding activity in occipital cortex(${\int}^{120min}_0$ OCC(t)dt). The purpose of this study was to examine the IPT pharmacokinetics and investigate the usefulness of simplified methods of (BG-OCC)/OCC, $R_A$, and $R_v$ which are often assumed that these values reflect the true values of $k_3/k_4$. The rate constants $K_1,\;k_2\;k_3$ and $k_4$ to be used for simulations were derived using [I-123]IPT SPECT and aterialized blood data with a standard three compartmental model. The sensitivities and time activity curves in BG and OCC were computed by changing $K_l$ and $k_3$(only BG) for every 5min over 2 hours. The values (BG-OCC)/OCC, $R_A$, and $R_v$ were then computed from the time activity curves and the linear regression analysis was used to measure the accuracies of these methods. The late constants $K_l,\;k_2\;k_3\;k_4$ at BG and OCC were $1.26{\pm}5.41%,\;0.044{\pm}19.58%,\;0.031{\pm}24.36%,\;0.008{\pm}22.78%$ and $1.36{\pm}4.76%,\;0.170{\pm}6.89%,\;0.007{\pm}23.89%,\;0.007{\pm}45.09%$, respectively. The Sensitivities for ((${\Delta}S/S$)/(${\Delta}k_3/k_3$)) and ((${\Delta}S/S$)/(${\Delta}K_l/K_l$)) at 30min and 120min were measured as (0.19, 0.50) and (0.61, 0,23), respectively. The correlation coefficients and slopes of ((BG-OCC)/OCC, $R_A$, and $R_v$) with $k_3/k_4$ were (0.98, 1.00, 0.99) and (1.76, 0.47, 1.25), respectively. These simulation results indicate that a late [I-123]IPT SPECT image may represent the distribution of the dopamine transporters. Good correlations were shown between (3G-OCC)/OCC, $R_A$ or $R_v$ and true $k_3/k_4$, although the slopes between them were not unity. Pharmacokinetic computer simulations may be a very useful technique in studying dopamine transporter systems.

• Korean Journal of Health Education and Promotion
• /
• v.20 no.2
• /
• pp.35-61
• /
• 2003

Background： The purpose of this study was to develop a structured and individualized smoking prevention program for adolescents by utilizing a multimedia computer-assisted instruction model and to empirically assess its effect. Method： For the purpose of this study, a guide book of smoking prevention program for middle and high school students was developed as the first step. The contents of this book were summarized and developed into an actual multimedia CAI smoking prevention program according to the Gane ＆ Briggs instructional design and Keller's ARCS motivation design models as the second step. At the final step, the short-tenn effects of this program were examined by an experiment. This experiment were made for middle school and high school students and the quasi experimental design was the pretest - intervention - posttest. The measured data was attitude, belief, and knowledge about smoking, interest in the program, and learning motivation. Result： The results of this study were as follows： First, the guide book of a smoking prevention program was developed and the existing literature on adolescent smoking was analyzed to develop the content of the guide book. Then the curriculum was divided into three main domains on tobacco and smoking history, smoking and health, adolescent smoking and each main domain was divided into sub-domains. Second, the contents of the guide book were translated into a multimedia CAI program of smoking prevention througn Powerpoint software according to the instructional design theory. The characteristics of this program were interactive, learner controllable, and structured The program contents consisted of entrance(5.6％), history of tobacco(30％), smoking and health(38.9％), adolescent smoking(22.2％), video(4.7％), and exit(1.6％). Multimedia materials consisted of text(121), sound and music, image(still 84, dynamic 32), and videogram(6). The program took about 40 minutes to complete. Third, the results on analysis of the program effects were as follows： 1) There was significant knowledge increase between the pre-test and post-test with total mean difference 3.44, and the highest increase was in the 1st grade students of high school(p＜0.001). 2) There was significant decrease in general belief on smoking between the pre-test and post-test with total mean difference 0.28. In subgroup analysis, the difference was significantly higher in the 1st grade of high school (p<0.001), low income class (p<0.001), and daily smokers (p<0.01). 3) There was no significant difference in attitudes on his personal smoking between the pre-test and post-test. 4) The interest in the program seemed to lower as students got older. The score of motivation toward this prevention program was the highest in the middle school 3rd grade. Among sub-domains of motivation, the confidence score was the highest. Conclusion： To be most effective, the smoking prevention program for adolescents should utilize the most up-to-date and accurate information on smoking, and then instructional material should be developed so that the learners can approach the program with enjoyment. Through this study, a guide book with the most up-to-date information was developed and the multimedia CAI smoking prevention program was also developed based on the guide book. The program showed positive effect on the students' knowledge and belief in smoking.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.28 no.2
• /
• pp.219-227
• /
• 2001

Little is known about processing mechanism of pain sensation of the oral cavity at the 1st synapse of trigeminal sensory nuclei. Serial ultrathin sections of tooth pulp afferent terminals, identified by the transganglionic transport of 1% wheatgerm agglutinin conjugated horseradish peroxidase, were investigated with electron microscope. Quantitative ultrastructural analysis was performed on digitizing tablet connected to Macintoshi personal computer (software; NIH Image 1.60, NIH, Bethesda, MD). Labeled boutons could be classified into two types by the shapes of containing vesicles : S bouton, which contained mainly spherical vesicles (Dia. 45-55 nm) and few large dense cored vesicles (Dia, 80-120nm), and LDCV bouton, which contained spherical vesicles as well as large number of large dense cored vesicles. Most of the parameters on the ultrastructural characteristic and synaptic organization of labeled boutons were similar between S and LDCV boutons, except shapes of containing vesicles. Majority of the labeled boutons showed simple synaptic arrangement. The labeled boutons were frequency presynaptic to dendritic spine, and to a lesser extent, dendritic shaft. They rarely synapsed with soma and adjacent proximal dendrite. A small proportion of labeled boutons made synaptic contacts with presynaptic, pleomorphic vesicles containing endings and synaptic triad. Morphometric parameters of labeled boutons including volume and surface area, total apposed area, mitochondrial volume, active zone area, vesicle number and density showed wide variation and these were not significantly different between S and LDCV boutons. The present study revealed characteristic features on ultrastructure and synaptic connection of pulpal afferents which may involved in transmission of oral pain sensation.

• The korean journal of orthodontics
• /
• v.36 no.1 s.114
• /
• pp.14-29
• /
• 2006

Developments in computer technology have made possible the 3-dimensional (3-D) evaluation of hard and soft tissues in orthodontic diagnosis, treatment planning and post-treatment results. In this study, Korean adults with normal occlusion (male 30, female 30) were scanned by a 3-D laser scanner, then 3-D facial images formed by the Rapidform 2004 program (Inus Technology Inc., Seoul, Korea.). Reference planes in the facial soft tissue 3-D images were established and a 3-D coordinate system (X axis-left/right, Y axis-superior/inferior, Z axis-anterior/posterior) was established by using the soft tissue nasion as the zero point. Twenty-nine measurement points were established on the 3-D image and 43 linear measurements, 8 angular measurements, 29 linear distance ratios were obtained. The results are as follows; there were significant differences between males and females in the nasofrontal angle $(male:\;142^{\circ},\;female:\;147^{\circ})$ and transverse nasal prominence $(male:\;112^{\circ},\;female:\;116^{\circ})$ (p<0.05). The transverse upper lip prominence was $107^{\circ}$ in males, $106^{\circ}$ in females and the transverse mandibular prominence was $76^{\circ}$ in both males and females. Li-Me' was 0.4 times the length of Go-Me'(mandibular body length) and the mouth height was also 0.4 times the width of the mouth width. The linear distance ratio from the coronal reference plane of FT, Zy, Pn, ULPm, Li, Me' was -1/-1/1/0.5/0.5/-0.6 respectively. The 3-D facial model of Korean adults with normal occlusion were be constructed using coordinate values and linear measurement values. These data may be used as a reference in 3-D diagnosis and treatment planning for malocclusion and dentofacial deformity patients and applied for 3-D analysis of facial soft tissue changes before and after orthodontic treatment and orthognathic surgery.