• Journal of the Korean Society of Radiology
• /
• v.10 no.2
• /
• pp.81-87
• /
• 2016

In this study we proposed a texture feature analysis algorithm that distinguishes between a normal image and a diseased image using CT images of some fatty liver patients, and generates both Eigen images and test images which can be applied to the proposed computer aided diagnosis system in order to perform a quantitative analysis for 6 parameters. And through the analysis, we derived and evaluated the recognition rate of CT images of fatty liver. As the results of examining over 30 example CT images of fatty liver, the recognition rates representing a specific texture feature-value are as follows: some appeared to be as high as 100% including Average Gray Level, Entropy 96.67%, Skewness 93.33%, and Smoothness while others showed a little low disease recognition rate: 83.33% for Uniformity 86.67% and for Average Contrast 80%. Consequently, based on this research result, if a software that enables a computer aided diagnosis system for medical images is developed, it will lead to the availability for the automatic detection of a diseased spot in CT images of fatty liver and quantitative analysis. And they can be used as computer aided diagnosis data, resulting in the increased accuracy and the shortened time in the stage of final reading.

• Journal of Fashion Business
• /
• v.14 no.1
• /
• pp.86-105
• /
• 2010

Vintage fashion is a lot influenced by colors because an emotion is transmitted via images of "old feeling", "worn-out feeling" and "faded feeling" etc. Colors are visual sensation occurring at a time when lights stimulate an eye, which is a representative factor which humans first perceive when they touch objects. And colors in clothing function as a critical element which indicates an individual's impression and character as well as aesthetic sensation. In this study, I examined on the theoretical consideration and aesthetic characteristics via the previous literature on vintage fashion and colors. As an empirical study, I investigated on the colors of vintage fashion appearing in Pr$\hat{e}$t-$\grave{a}$-porter Collections, Paris from Spring/Summer, 2003 to Fall/Winter 2008. As a way for study, I investigated into the total 197 vintage fashion photos and calculated their RGB values by using photoshop. And I converted the values of the colors extracted into H V/C values by using Munsell Conversion Version 9.0.6 and analyzed on Munsell System of 10 Color Notation and the PCCS colors, classifying a color scheme by visual sensation measurement. The result of analyzing on the concept of vintage fashion and its color characteristics is as follows; Vintage fashion made an appearance the most in 2003 and 2004 and its colors appeared a lot in Y, YR, R and PB lines. Color tone concentrated on black and white, achromatic color and low chroma colors in a grayish line, chromatic color. Thus, the study found that colors suitable for a "worn-out", "faded" and "old" image are properly reflected in vintage fashion rather than a clear and bright background. In a color scheme, I found contrast color and same color appearing a lot, which gave an unharmonious feeling and a smack of the country. The study reveals that the color characteristic of vintage fashion is relatively diverse and complex in color, color tone or shade and color scheme, which shows a color trend which reflects a non-constructive and complex coordination characteristic instead of a standardized simple and clear image.

• Journal of the Korean Society of Radiology
• /
• v.12 no.5
• /
• pp.631-636
• /
• 2018

The problem that the existing the magnetic resonance image (MRI) was prone to have not only long readout duration and low bandwidth in the phase-encode direction, but also geometric distortion was pointed out. The purpose of this study is to identify the usefulness of FOCUS-DWI through comparing FOCUS-DWI with the Conventional-DWI on a degree of uniformity and artifacts caused by the distance change in the central axis within the magnetic field. In terms of artifacts, there happened irregular striped artifacts in the Conventional-DWI technique, which in particular, more often arose in the central axis. Also, the overlap of imaging drastically increased. By contrast, there were no irregular striped artifacts in the FOCUS-DWI technique. In conclusion, it was found that the FOCUS-DWI technique was superior to the Conventional-DWI technique in terms of artifacts, the overlap of imaging, and a degree of uniformity. In addition, there was no difference of the change in distance from the central axis between the FOCUS-DWI technique and the Conventional-DWI technique. Thus, it is considered the FOCUS-DWI technique having less imaging distortion and high image quality will be highly clinically used.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.252-259
• /
• 2007

With the rapid development of multimedia applications and wireless communication networks, consumer demand for video-over-wireless capability on mobile computing systems is growing rapidly. In this regard, this paper introduces YUV-aware instructions that enhance the performance and efficiency in the processing of color image and video. Traditional multimedia extensions (e.g., MMX, SSE, VIS, and AltiVec) depend solely on generic subword parallelism whereas the proposed YUV-aware instructions support parallel operations on two-packed 16-bit YUV (6-bit Y, 5-bits U, V) values in a 32-bit datapath architecture, providing greater concurrency and efficiency for color image and video processing. Moreover, the ability to reduce data format size reduces system cost. Experiment results on a representative dynamically scheduled embedded superscalar processor show that YUV-aware instructions achieve an average speedup of 3.9x over the baseline superscalar performance. This is in contrast to MMX (a representative Intel#s multimedia extension), which achieves a speedup of only 2.1x over the same baseline superscalar processor. In addition, YUV-aware instructions outperform MMX instructions in energy reduction (75.8% reduction with YUV-aware instructions, but only 54.8% reduction with MMX instructions over the baseline).

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.1
• /
• pp.63-66
• /
• 2009

Purpose: ACR (American College of Radiology) offers variable parameters to PET/CT quality control by using ACR Phantom. ACR Phantom was made to evaluate parameters which are uniformity, attenuation, scatter, contrast and resolution. Manual analysis method wasn't good for the use of QC because values of parameter were changed as it may user and it takes long time to analysis. Ki-Chun Lim, a nuclear scientist in AMC, developed program that automatically analysis values of parameter by using ACR Phantom to overcome above problems. In this study, we evaluated automatic analysis program's usability, through the comparing SUV of each method, reproducibility of SUV when repeated analysis and the time required. Materials and Methods: Using Flangeless Esser PET Phantom, the ideal ratio of 4 : 1 hot cylinder and BKG but it actually showed a ratio of 3.89 to 1 hot cylinder and BKG. SIEMENS Biograph True Point 40 was used in this study. We obtained images using ACR phantom at Fusion WB PET Scan condition (2 min/bed) and 120 kV, 100 mAs CT condition. Using True X method, 3 iterations, 14 subsets, Gaussian filter, FWHM 4 mm and Zoom Factor 1.0, $168{\times}168$ image size. We obtained Max. & Min. SUV and SUV Mean values at Cylinder (8, 12, 16, 25 mm, Air, Bone, Water, BKG) by automatic program and obtained SUV by manual method. After that, we compared manual and automatic method. we estimate the time required from opened the image data to final work sheet was completed. Results: Automatic program always showed same result and same the time required. At 8, 12, 16 and 25 m cylinder, manual method showed 6.69, 3.46, 2.59, 1.24 CV values. The larger cylinder size became, the smaller CV became. In manual method, bone, air, water's CV were over 9.9 except BKG (2.32). Obtained CV of Mean SUV showed BKG was low (0.85) and bone was high (7.52). The time required was 45 second, 882 second respectably. Conclusions: As a result of difference automatic method and manual method, automatic method showed always same result, manual method showed that the smaller hot cylinders became, the lager CV became. Hot cylinders mean region size, the smaller hot cylinder size becomes we had some trouble in doing ROI poison setting. And it means increase in variation of SUV. The Study showed the time required of automatic method was shorten then manual method.

• Journal of the Korean Society of Radiology
• /
• v.9 no.6
• /
• pp.369-374
• /
• 2015

In this study we proposed a texture feature analysis algorithm that distinguishes between a normal image and a diseased image using CT images of some brain hemorrhage patients, and generates both Eigen images and test images which can be applied to the proposed computer aided diagnosis system in order to perform a quantitative analysis for 6 parameters. And through the analysis, we derived and evaluated the recognition rate of CT images of brain hemorrhage. As the results of examining over 40 example CT images of brain hemorrhage, the recognition rates representing a specific texture feature-value are as follows: some appeared to be as high as 100% including average gray level, average contrast, smoothness, and Skewness while others showed a little low disease recognition rate: 95% for uniformity and 87.5% for entropy. Consequently, based on this research result, if a software that enables a computer aided diagnosis system for medical images is developed, it will lead to the availability for the automatic detection of a diseased spot in CT images of brain hemorrhage and quantitative analysis. And they can be used as computer aided diagnosis data, resulting in the increased accuracy and the shortened time in the stage of final reading.

• Journal of the Korea Concrete Institute
• /
• v.20 no.4
• /
• pp.513-522
• /
• 2008

The fiber dispersion performance in fiber-reinforced cementitious composites is a crucial factor with respect to achieving desired mechanical performance. However, evaluation of the fiber dispersion performance in the composite PVA-ECC (Polyvinyl alcohol-Engineered Cementitious Composite) is extremely challenging because of the low contrast of PVA fibers with the cement-based matrix. In the present work, an enhanced fiber detection technique is developed and demonstrated. Using a fluorescence technique on the PVA-ECC, PVA fibers are observed as green dots in the cross-section of the composite. After capturing the fluorescence image with a Charged Couple Device (CCD) camera through a microscope. The fibers are more accurately detected by employing a series of process based on a categorization, watershed segmentation, and morphological reconstruction.

• The Journal of Engineering Geology
• /
• v.18 no.4
• /
• pp.537-543
• /
• 2008

To effectively delineate the foundation of stone relics by GPR and seismic refraction methods, a geological engineering model was constructed with alternating layer of soil and gravel to a depth of 3 m. This study was aimed at mapping the boundaries of model ground structure and interfaces of alternating layer using the various frequency antenna in GPR survey and seismic velocities. Compared to the resolution from the high frequency antenna, the image resolution from the survey using 100 Hz antenna is the lower, but with the deeper image coverage. On the contrast, the deeper structure was not mapped in the higher frequency data due to higher absorption effect, but the shallow layered zone was distinctively resolved. Therefore subsurface images were effectively provided by integrating the data with 100 MHz and 450 MHz antennas for the deep and shallow structures, respectively. Regarding the seismic refraction data, the boundaries of the model and interface of the alternating layers were not successfully mapped due to the limit of the survey length. However, the equivalent contours of low velocity extended deep as considerable velocity contrasts with surrounding ground.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.