• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Journal of the Korean Society of Radiology
• /
• v.82 no.1
• /
• pp.2-11
• /
• 2021

More than 4 million women undergo breast cancer (BC) screening with mammography each year in Korea. Digital mammography (DM) was introduced in 2000, and it has been reported to have a higher diagnostic accuracy than screen-film mammography (SFM) or computed radiography (CR) in women with dense breasts. According to a study using data from the National Cancer Screening Program for BC, the diagnostic accuracy of DM was higher than those of SFM and CR, regardless of age, breast density, and screening round. Currently, despite high supply rate among OECD countries, the distribution of DM equipment is approximately 35% in Korea. For quick replacement with DM, it will be necessary to improve its fee for the National Health Insurance and support an educational program for radiologists. In addition, efforts should be made to increase the accessibility of DM.

• Journal of Environmental Science International
• /
• v.29 no.5
• /
• pp.519-529
• /
• 2020

The purpose of this study was to provide basic health care data for the climate aspects of park re-cultivation by evaluating air ions according to the type of vegetation in the valley and upper slopes of the mountain park. Simple negative or positive air ions were expected to show the same tendencies, so they were analyzed in terms of correcting the air ion index. By analyzing the air ions according to the topography, it was found that valley > slope in terms of the air ion index. When analyzing air ions according to tree species, we found that evergreen conifers in the valley > the deciduous broad-leaved trees in the valley > the evergreen conifers in the slope = the deciduous broad-leaved trees in the slope. For DBH(Diameter at breast height), the valley large pole > slope large pole > slope medium hard wood, while crown density was analyzed as valley dense > slope dense> valley proper > slope proper. Layered structure analysis showed that the multi-layer structure of the valley > multi-layer structure of the slope = the single-layer structure of the valley > the single-layer structure of the slope. The correlation coefficient was determined according to vegetation type and air ion index in the order of DBH > crown density > layer structure > geomorphic structure. In this study, limits exist except for ridge line, valley, and slopes in urban mountain parks. Therefore, analysis should be made considering both topographical structure and various vegetation types in future studies of air ions.

• Journal of Animal Science and Technology
• /
• v.62 no.4
• /
• pp.577-586
• /
• 2020

This study was to investigate the effect of salt alone or in combination with phosphate on physicochemical and textural properties, and chemical interactions of low-fat model sausages. pH, color, expressible moisture (EM), cooking loss (CL), proximate analysis, textural profile analysis and low-vacuum scanning electron microscopy were performed. As salt content increased, color tended to decrease, as did EM and CL parameters, indicating that the ability to retain moisture was improved with increased salt levels (p < 0.05). In addition, textural hardness, gumminess and chewiness all increased with increasing salt (p < 0.05). Sausages with 0.3% salt showed the lowest cohesiveness compared to those with salt levels higher than 0.3% (p < 0.05). Addition of sodium tripolyphosphate (STPP) increased pH of sausages. Increasing salt and STPP did not affect lightness (p > 0.05), but did increase redness and yellowness (p < 0.05). The moisture content was higher when the salt and STPP contents were increased (p < 0.05), but no differences in the fat and protein contents (%) were observed (p > 0.05). EM and CL tended to decrease with increasing salt and STPP. In textural properties, the combination of 1.8% salt and 0.3% STPP was the best among other treatment (p < 0.05). Surface microstructure showed a flat and dense structure with increasing salt and STPP. Since the addition of salt and phosphate improved the functionality, textural and physicochemical properties of meat products in this study, meat products will need to be developed in line with consumer's preference.

• Clinical and Experimental Pediatrics
• /
• v.52 no.2
• /
• pp.152-158
• /
• 2009

Reduced fetal growth is independently associated with increased risk of health problems in later life, particularly type 2 diabetes and cardiovascular diseases. Insulin resistance appears to be a key component underlying these metabolic complications. It is suggested that detrimental fetal environment may program insulin resistance syndrome. An insulin-resistant genotype may also result in both low birth weight and insulin resistance syndrome, and it is likely that the association of low birth weight with insulin resistance is the result of both genetic and environmental factors. Early postnatal rapid catch-up growth is closely related to risk for subsequent metabolic diseases. Fat mass is strikingly reduced in neonates born small for gestational age (SGA), and recent data suggest that insulin resistance seen in catch-up growth is related to the disproportionate catch-up in fat mass compared with lean mass. Endocrine disturbances are also recognized in SGA children, but overt clinical problems are infrequent in childhood. Cognitive impairment is reported in some children born SGA, especially those who do not show catch-up growth, in whom early neurodevelopmental evaluation is required. Breast feeding, also known to be protective against the long-term risk of obesity, may prevent some intellectual impairment in SGA children. Calorie-dense feeding does not seem to be appropriate in SGA infants. We must balance the positive effect of nutrition on neural development against rapid fat deposition and the future risk of insulin resistance.

• Journal of Environmental Science International
• /
• v.25 no.10
• /
• pp.1407-1415
• /
• 2016

In this study, we investigated the relationship between noise reduction and the community structure of nine groups of typical plant communities as well as the reduction in noise at different frequencies. The semantic differential method was adopted to explore the perception of noise reduction. The results indicated that there was a significantly positive correlation between noise reduction and coverage, a significantly negative correlation between noise reduction and bifurcate height, and a negative correlation between noise reduction and bare rate. However, there was no significant correlation between noise reduction and height, diameter at breast height, or crown width. The reduction of middle-frequency noise was better than that of low- and high-frequency noise. The indicators "quiet" and "calm" showed that plant communities could reduce the noise perceived by humans. However, overly dense woodland caused nervousness, fear, depression, and other negative effects. Relatively open environments and those with large forest gaps obtained the highest evaluation.

• Korean Journal of Radiology
• /
• v.25 no.6
• /
• pp.511-517
• /
• 2024

Objective: To prospectively investigate the influence of the menstrual cycle on the background parenchymal signal (BPS) and apparent diffusion coefficient (ADC) of the breast on diffusion-weighted MRI (DW-MRI) in healthy premenopausal women. Materials and Methods: Seven healthy premenopausal women (median age, 37 years; range, 33-49 years) with regular menstrual cycles participated in this study. DW-MRI was performed during each of the four phases of the menstrual cycle (four examinations in total). Three radiologists independently assessed the BPS visual grade on images with b-values of 800 sec/mm² (b800), 1200 sec/mm² (b1200), and a synthetic 1500 sec/mm² (sb1500). Additionally, one radiologist conducted a quantitative analysis to measure the BPS volume (%) and ADC values of the BPS (ADC_BPS) and fibroglandular tissue (ADC_FGT). Changes in the visual grade, BPS volume (%), ADC_BPS, and ADC_FGT during the menstrual cycle were descriptively analyzed. Results: The visual grade of BPS in seven women varied from mild to marked on b800 and from minimal to moderate on b1200 and sb1500. As the b-value increased, the visual grade of BPS decreased. On b800 and sb1500, two of the seven volunteers showed the highest visual grade in the early follicular phase (EFP). On b1200, three of the seven volunteers showed the highest visual grades in EFP. The BPS volume (%) on b800 and b1200 showed the highest value in three of the six volunteers with dense breasts in EFP. Three of the seven volunteers showed the lowest ADC_BPS in the EFP. Four of the seven volunteers showed the highest ADC_BPS in the early luteal phase (ELP) and the lowest ADC_FGT in the late follicular phase (LFP). Conclusion: Most volunteers did not exhibit specific BPS patterns during their menstrual cycles. However, the highest BPS and lowest ADC_BPS were more frequently observed in EFP than in the other menstrual cycle phases, whereas the highest ADC_BPS was more common in ELP. The lowest ADC_FGT was more frequent in LFP.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.4
• /
• pp.67-74
• /
• 2016

Drone images with high spatial resolution are emerging as an alternative to previous studies with extraction limits in high density forests. Individual tree in the dense forests were extracted from drone images. To detect the individual tree extracted through the image segmentation process, the image segmentation results were compared between the combination of DSM and all R,G,B band and the combination of DSM and R,G,B band separately. The changes in the tree density of a deciduous forest was experimented by time and image. Especially the image of May when the forests are dense, among the images of March, April, May, the individual tree extraction rate based on the trees surveyed on the site was 50%. The analysis results of the width of crown showed that the RMSE was less than 1.5m, which was the best result. For extraction of the experimental area, the two sizes of medium and small trees were extracted, and the extraction accuracy of the small trees was higher. The forest tree volume and forest biomass could be estimated if the tree height is extracted based on the above data and the DBH(diameter at breast height) is estimated using the relational expression between crown width and DBH.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.2
• /
• pp.1-12
• /
• 2017

This study aims to provide the basic habitat data for the alternative breeding sites of Family Ardeidae including Ardea cinerea, Egretta alba modesta, Egretta intermedia, Egretta garzetta, Bubulcus ibis and Nycticorax nyciticorax. Species numbers, flight directions for detecting foraging grounds and current vegetation structure were investigated nesting at Gunsan urban forest area. Data were collected over a period of 10 weeks, from 15 June - 31 August 2014. The total nest and population of Family Ardeida were 684 and 1,712 respectively. Percentage of birds observed flying in 8 major compass directions were as follows. 57.27% of all birds were observed flying northwest, 22.09% were observed flying south and 13.40% were flying north. For possible foraging areas, to the northwest, there are Geumgang river tidal flats, and to the south, paddy fields and streams within 2km. Flying directions by species (${\chi}^2=287.18$, P<.001, Cramer's V=0.12) and by seasons(${\chi}^2=839.94$, P<.001, Cramer's V=0.19) showed significant difference statistically. In relation between species and directions, 60.31% and 24.05% of Bubulcus ibis and 59.40% and 23.00% of Ardea cinerea were observed flying northwest and south respectively. Vegetation in the sites consist of an overstory of 3 to 7 species. At site 1, Pinus thunbergii was the dominant species and site 2, Chamaecyparis obtusa. Understory vegetation is composed of shrubs, saplings and small trees of Chamaecyparis obtusa, Quercus acutissima, Smilax china and Platycarya strobilacea. Egrets and herons usually nested at the dense population and canopy overlayed forest, and especially branches and leaves of smallwood with less than 10cm of breast height diameter were relatively severely damaged due to the nesting and excreta.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.721-734
• /
• 2001

This paper proposed automated methods for the detection of breast mass. We analysed characteristic of the mass by using the features on mammograms. The homogeneity was used to distinguish mass and abnormal homogeneous tissue from the Cooper's ligament and multiple threshold method was used to deal with the high density candidates. By using the 8-connectivity, the first step candidates were selected. We generated the dualistic images of each candidate in which we regard the gray value as topographic height information. From these candidates, the second candidates were selected by comparing the circularity and the distribution rates. The final detection was done with the method in which we generated the template of each candidate and compared each other. From these methods, we grade the order from the candidate. We applied the algorithm to the 136 mammograms and compared to the radiologist's outlines of the leisions. The detection resulted that the sensitivity of the proposed methods was 93.38% and 97.63% FP(False positive) which we can segmented mass in the first grade in the 124 cases.