• ETRI Journal
• /
• v.44 no.5
• /
• pp.816-825
• /
• 2022

Nondestructive testing, which can monitor a product's interior without disassembly, is becoming increasingly essential for industrial inspection. Computed laminography (CL) is widely used in this application, as it can reconstruct a product, such as a printed circuit board, into a three-dimensional (3D) high-magnification image using X-rays. However, such high-magnification scanning environments can be affected by minute vibrations of the CL device, which can generate motion artifacts in the 3D reconstructed image. Since such vibrations are irregular, geometric corrections must be performed at every scan. In this paper, we propose a geometry calibration method that can correct the geometric information of CL scans based on the image without using geometry calibration phantoms. The proposed method compares the projection and digitally reconstructed radiography images to measure the geometric error. To validate the proposed method, we used both numerical phantom images at various magnifications and images obtained from real industrial CL equipment. The experiment results confirmed that sharpness and contrast-to-noise ratio (CNR) were improved.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.31-33
• /
• 2007

Devising an efficient one-pass frequent pattern mining algorithm has been an issue in data mining research in recent past. Pattern growth algorithms like FP-Growth which are found more efficient than candidate generation and test algorithms still require two database scans. Moreover, FP-growth approach requires rebuilding the base-tree while mining with different support counts. In this paper we propose an item-based tree, called I-Tree that not only efficiently mines frequent patterns with single database scan but also provides multiple mining scopes with multiple support thresholds. The 'build-once-mine-many' property of I-Tree allows it to construct the tree only once and perform mining operation several times with the variation of support count values.

• Korean Journal of Digital Imaging in Medicine
• /
• v.13 no.2
• /
• pp.63-69
• /
• 2011

Table strapis patient fixture for securing the patient movements and falls. if it designed to measure the abdominal circumference and used as an indicator of dose selection at CT scan. it will prevent the overexposure of dose without degradation of image quality and efficiently manage dose of each type of body to technician to deal with CT. First, in order to compare the dose used in CT image and qualitative characteristics. reference image is obtained by examining the abdominal phantom in same conditions with the hospital 120 kVp, 200 mAs, D-Dom (Dynamic Dose Of Modulation). SNR, PSNR, RMSE, MAE, CTDIvol of CT images are compared with reference image. for comparing with reference image, the image that Umbilicus level image of Abdomen CT is stored in the PACS were used. For comparison, the top 12 o'clock portion of the air drawn from the same ROI was measured. CTDIvol, mAs, etc. In order to analyze the characteristics of the image, by measuring the length of the umbilicus circumference, pattern of the dose was analyzed. by using the analyzed perimeter and dose information, To be identified visually, fixed band that scale marked were produced. Use them, If the length of circumference of less than 60 cm 100 mAs, Case of 61~80 cm 120 mAs, Case of 80~100 cm 150 mAs, more than 100 cm 200 mAs, dose selection based on the perimeter, the image was applied. by compare analyzed with the Reference Image, image quality was assessed. by compare with existing tests that equally 200 mAs applied, How much was confirmed that the dose reduction. 1. Depending on the Abdominal circumference, the average PSNR(dB) of the image that differently dose applied was 45.794. 2. Comparing with existing test. the dose of scan that adjusted the mAs depending on the circumference was decreased about 40%. SNR and PSNR of the image that obtained by adjusting the standard mAs based on dose modulation were not much different. Therefore, By choosing a low mAs. dose reduction can be obtained. and the dose selection method that measured Abdominal circumference using a fixed band can protect the overexposure and uniformly apply dose of each type of body to technician to deal with CT.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.500-521
• /
• 2021

Echocardiography, an ultrasound scan of the heart, is regarded as the primary physiological test for heart disease diagnoses. How an echocardiogram is interpreted also relies intensively on the determination of the view. Some of such views are identified as standard views because of the presentation and ease of the evaluations of the major cardiac structures of them. However, finding valid cardiac views has traditionally been time-consuming, and a laborious process because medical imaging is interpreted manually by the specialist. Therefore, this study aims to speed up the diagnosis process and reduce diagnostic error by providing an automated identification of standard cardiac views based on deep learning technology. More importantly, based on a brand-new echocardiogram dataset of the Asian race, our research considers and assesses some new neural network architectures driven by action recognition in video. Finally, the research concludes and verifies that these methods aggregating dynamic information will receive a stronger classification effect.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• Childhood Kidney Diseases
• /
• v.17 no.2
• /
• pp.110-116
• /
• 2013

Purpose: The $^{99m}Tc$-Dimercaptosuccinic acid (DMSA) renal scan is used primarily for the diagnosis of renal scarring and acute pyelonephritis in children with urinary tract infections (UTI). This study aimed to evaluate clinical differences based on the positive or negative results of DMSA scans and kidney ultrasonography (US) in pediatric UTI. Method: We retrospectively reviewed 142 pediatric patients with UTI who were admitted to Myongji Hospital from January 2004 to December 2012. We performed a comparative analysis of clinical parameters such as age, sex, white blood cell (WBC) count, neutrophil count, blood urea nitrogen (BUN) level, creatinine (Cr) level, C-reactive protein (CRP) level, and durations of hospitalization and fever, grouped by the results of the DMSA scans and kidney US. Results: The mean age of the patients was $33.8{\pm}48.3$ months, and 78 (55%) were male. Fifty-two patients had abnormal DMSA findings, and 71 patients had abormal kidney US findings (test positive groups). In the DMSA scan positive group, there were significant differences in age, WBC counts, neutrophil counts, CRP level, BUN level, Cr level, hospitalization duration, number of abnormal findings on kidney US, and incidence of vesicoureteral reflux (VUR) compared with the scan negative group. The kidney US positive group had significant differences in age, neutrophil count, CRP level, BUN level, Cr level, hospitalization duration, number of abnormal findings on the DMSA scans, and more frequent VUR compared with the US negative group. Conclusion: Our data suggest that there were no major differences in clinical parameters based on the results of the DMSA scans compared with kidney US in pediatric UTI. However, as kidney US and DMSA scan were performed to predict VUR, the sensitivity and negative predictive value was increased.

• Journal of the Ergonomics Society of Korea
• /
• v.21 no.3
• /
• pp.59-79
• /
• 2002

The purposes of the study were to present the optimum slacks pattern for elementary school girls and to compare and evaluate wearing ease of the slacks. 3D scans using the Cyberware PS motion platform were carried out for 3 subjects who have different body type. The automatic drafting method was programmed by AutoLISP in CAD. Wearing tests using 3D Scanner was done for evaluation of fitness of slacks. Regression analysis, analysis of variance and post-hoc test were performed for statistical analysis of the data by SPSS program. The procedure and results were as follows: The slacks construction components for pattern drafting were derived from 10 horizontal section maps obtained from 3D scans. The automatic drafting was based on the measurements of slacks construction components and the curve of crotch line. The crotch line was drafted using of the arc function in AutoCAD. The total crotch length was calculated using the multiple regression equation. Wearing test represented that the slacks pattern developed to accomodate individual body measurements was estimated more highly than existing patterns.

• Dementia and Neurocognitive Disorders
• /
• v.22 no.2
• /
• pp.61-68
• /
• 2023

Background and Purpose: Analyzing brain amyloid positron emission tomography (PET) images to access the occurrence of β-amyloid (Aβ) deposition in Alzheimer's patients requires much time and effort from physicians, while the variation of each interpreter may differ. For these reasons, a machine learning model was developed using a convolutional neural network (CNN) as an objective decision to classify the Aβ positive and Aβ negative status from brain amyloid PET images. Methods: A total of 7,344 PET images of 144 subjects were used in this study. The 18F-florbetaben PET was administered to all participants, and the criteria for differentiating Aβ positive and Aβ negative state was based on brain amyloid plaque load score (BAPL) that depended on the visual assessment of PET images by the physicians. We applied the CNN algorithm trained in batches of 51 PET images per subject directory from 2 classes: Aβ positive and Aβ negative states, based on the BAPL scores. Results: The binary classification of the model average performance matrices was evaluated after 40 epochs of three trials based on test datasets. The model accuracy for classifying Aβ positivity and Aβ negativity was (95.00±0.02) in the test dataset. The sensitivity and specificity were (96.00±0.02) and (94.00±0.02), respectively, with an area under the curve of (87.00±0.03). Conclusions: Based on this study, the designed CNN model has the potential to be used clinically to screen amyloid PET images.

• Korean Journal of Biological Psychiatry
• /
• v.11 no.2
• /
• pp.155-164
• /
• 2004

Objective:The present study examined the association between basic neurocognitive functions and emotional recognition in chronic schizophrenia. Furthermore, to Investigate cognitive variable related to emotion recognition in Schizophrenia. Methods:Forty eight patients from the Yongin Psychiatric Rehabilitation Center were evaluated for neurocognitive function, and Emotional Recognition Test which has four subscales finding emotional clue, discriminating emotions, understanding emotional context and emotional capacity. Measures of neurocognitive functioning were selected based on hypothesized relationships to perception of emotion. These measures included:1) Letter Number Sequencing Test, a measure of working memory;2) Word Fluency and Block Design, a measure of executive function;3) Hopkins Verbal Learning Test-Korean version, a measure of verbal memory;4) Digit Span, a measure of immediate memory;5) Span of Apprehension Task, a measure of early visual processing, visual scanning;6) Continuous Performance Test, a measure of sustained attention functioning. Correlation analyses between specific neurocognitive measures and emotional recognition test were made. To examine the degree to which neurocognitive performance predicting emotional recognition, hierarchical regression analyses were also made. Results:Working memory, and verbal memory were closely related with emotional discrimination. Working memory, Span of Apprehension and Digit Span were closely related with contextual recognition. Among cognitive measures, Span of Apprehension, Working memory, Digit Span were most important variables in predicting emotional capacity. Conclusion:These results are relevant considering that emotional information processing depends, in part, on the abilities to scan the context and to use immediate working memory. These results indicated that mul- tifaceted cognitive training program added with Emotional Recognition Task(Cognitive Behavioral Rehabilitation Therapy added with Emotional Management Program) are promising.