• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1363-1369
• /
• 2018

Breast cancer is one of the most common cancers in women worldwide. In Korea, breast cancer is most common cancer in women followed by thyroid cancer. The purpose of this study is to evaluate the possibility of using deep - run model for segmentation of breast masses and to identify the best deep-run model for breast mass segmentation. In this study, data of patients with breast masses were collected at Asan Medical Center. We used 596 images of mammography and 596 images of gold standard. In the area of interest of the medical image, it was cut into a rectangular shape with a margin of about 10% up and down, and then converted into an 8-bit image by adjusting the window width and level. Also, the size of the image was resampled to $150{\times}150$. In Deconvolution net, the average accuracy is 91.78%. In U-net, the average accuracy is 90.09%. Deconvolution net showed slightly better performance than U-net in this study, so it is expected that deconvolution net will be better for breast mass segmentation. However, because of few cases, there are a few images that are not accurately segmented. Therefore, more research is needed with various training data.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4591-4596
• /
• 2023

Single-photon emission computed tomography SPECT image reconstruction methods have a significant influence on image quality, with filtered back projection (FBP) and ordered subset expectation maximization (OSEM) being the most commonly used methods. In this study, we proposed newly-designed adaptive non-blind deconvolution with a structural similarity (SSIM) index that can take advantage of the FBP and OSEM image reconstruction methods. After acquiring brain SPECT images, the proposed image was obtained using an algorithm that applied the SSIM metric, defined by predicting the distribution and amount of blurring. As a result of the contrast to noise ratio (CNR) and coefficient of variation evaluation (COV), the resulting image of the proposed algorithm showed a similar trend in spatial resolution to that of FBP, while obtaining values similar to those of OSEM. In addition, we confirmed that the CNR and COV values of the proposed algorithm improved by approximately 1.69 and 1.59 times, respectively, compared with those of the algorithm involving an inappropriate deblurring process. To summarize, we proposed a new type of algorithm that combines the advantages of SPECT image reconstruction techniques and is expected to be applicable in various fields.

• Proceedings of the KSMRM Conference
• /
• 2000.11a
• /
• pp.23-23
• /
• 2000

• Proceedings of the Korean Vacuum Society Conference
• /
• 1996.02a
• /
• pp.154-154
• /
• 1996

• Journal of The Korean Radiological Technologist Association
• /
• v.29 no.1
• /
• pp.152-152
• /
• 2003

• Bulletin of the Korean Chemical Society
• /
• v.7 no.5
• /
• pp.403-405
• /
• 1986

• 한국연소학회:학술대회논문집
• /
• 1997.06a
• /
• pp.45-50
• /
• 1997

An experimental study on LII signal images from soot particles in a flame has been carried out in order to investigate the effect of the incident laser characteristics. By changing the wavelength of the incident laser beam, the LII signal was saturated at smaller laser power with 532 nm than 1,064 nm. This implies that the larger absorption coefficient of soot particles at 532 nm would influence the LII signal characteristic. Using the deconvolution technique, the projected LII line images were coverted to reconstruct the local LII signals inside the beam. The results show that the LII images at ICCD camera result from the integration of LII signal across the laser beam.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.337-338
• /
• 2000

The perceptual filter for speech enhancement was analytically derived where the frequency content of the input noisy signal was made the same as that of the estimated clean signal in auditory domain. However, the analytical derivation should rely on the deconvolution associated with the spreading function in the psychoacoustic model, which results in an ill-conditioned problem. In order to cope with the problem associated with the deconvolution, we propose a novel psychoacoustic model based speech enhancement filter whose principle is the same as the perceptual filter, however the filter is derived by a constrained optimization which provides solutions to the ill-conditioned problem.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.2
• /
• pp.50.4-51
• /
• 2015

Current and planned deep multicolor wide-area cosmological surveys will map in detail the spatial distribution of galaxies and quasars over unprecedented volumes, and provide a number of objects with photometric redshifts more than an order of magnitude bigger than that of spectroscopic redshifts. Photometric information is statistically more significant for studying cosmological evolution, dark energy, and the expansion history of the universe at a fraction of the cost of a full spectroscopic survey, but intrinsically carries a bias due to noise in the distance estimates. We provide convolution- and deconvolution-based algorithms capable of removing this bias -- thus able to exploit the full cosmological information -- in order to reconstruct intrinsic distributions and correlations between distance-dependent quantities. We then show some direct applications of our techniques to the VIMOS Public Extragalactic Redshift Survey (VIPERS) and the Sloan Digital Sky Survey (SDSS) datasets. Our methods impact a broader range of studies, when at least one distance-dependent quantity is involved; hence, they will be useful for upcoming large-volume surveys, some of which will only have photometric information.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.411-413
• /
• 2003

In the images obtained from high altitude, several materials are mixed in one pixel and observed as a mixel. It makes difficult to separate the value of pure materials from obtained data. As mixel analysis, various techniques using Independent Component Analysis (ICA) and wavelet analysis, etc, were proposed. In this study, we applied to the ICA technique to real data collected by hyperspectral line sensor. Real data came under the influence of several effects regarded as basin on the convolution. We show that combining the ICA method with deconvolution improve it's estimation ability.