• 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.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.6
• /
• pp.79-92
• /
• 2017

To offer the basic data of vegetation restoration by buried seed of soil, this research was conducted at bare land and abandoned field in Yesan-gun. Germination plants of buried seed were consisted of 40 taxa (37 species, 3 varieties) in bare land, and 41 taxa (37 species, 4 varieties) in abandoned field. Classification of germination plants by family was the most in Gramineae, and emergent frequency of plots was the highest of Digitaria ciliaris. The soil depth of the most plants appearance was 2~5cm in bare land and 5~10cm in abandoned field, and the soil depth of the most population appearance was 0~2cm both in bare land and in abandoned field. Population number of buried seed germination was decreased according to soil depth. Crepidiastrum sonchifolium was a plant that population number of buried seed germination is the most. Similarity index was 0.33 in aerial part plants and buried seed plants, and 0.55 in bare land and abandoned field.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.27 no.4
• /
• pp.143-150
• /
• 1999

The purpose of this research is to find som ways to model tree forms more efficiently in reference with surveying structural data and handling parameters in plant Editor of AccuRender, the AutoCAD-based rendering software adopting the procedural plant modeling technique. In case of modelling a new tree, because it is efficient to modify an existing tree data as a template, we attempted to classify 81 species' data from existing plant library including conifers and deciduous tree. According to the qualitative characteristics and quantitative parameters of geometrical and branching structure, 8 types of tree form were classified with factor and cluster analysis. Some critical aspects found in the distributions of standardized scores of parameters in each type were discussed for explaining the tree forms intuitively. For adaptability of the resulted classification and typical parameters, 10 species of tree were measured and modelled, and proved to be very similar to the real structures of tree forms. CG or CAD-based plant modelling technique would be recommended not only as a presentation tool but for planting design, landscape simulation and assessment.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.7 no.2
• /
• pp.12-20
• /
• 2004

This study was carried out from January 1998 to December 1999 to report the revegetation of cutting-rock slopes and a design standard in the highway cut-slopes. The field data was collected from the 67 sites cutting-rock slopes of highways, local roads, and field test. As the result of analyze, cutting-rock slopes revegetation measures were 16 types. There were Vine planting(3 types), Hydroseeding measures with seed-fertilizer-soil materials(5 types), Vegetaion-base spraying measures(5 types), and Stability measures(3 types). The factors affecting the plant coverage rates of cutting-rock slopes were the slope gradient, the slope width and direction. The plant coverage rate decreases in the condition of steep slope and long slope width and length(height). In addition, the plant coverage rates of the westward and southward were lower than that of the northward and eastward. Most dominant species were Zoysia japonica, Lespedeza cyrtobotrya, Lespedeza cuneata, Rubus crataegifolius, Miscanthus sinensis, Arrundinella hirta, Themeda triandra, and Oenothera odorata. Exotic species were Eragrostis curvula(Weeping lovegrass), Dactylis glomerata Orchardgrass), Lolium perenne(Perennial ryegrass), and Festuca arundinacea(Tall fescue). It is recommended to adjust the proposed factor as environment, topsoil, classification of rock, field condition and characteristic related with revegetation measures on slopes for the presentation of revegetation standard.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.42 no.4
• /
• pp.30-36
• /
• 2014

This study was conducted to determine the causes of unreasonable prices and small numbers of azalea cultivars by analyzing the price trends and the number of azalea cultivars announced over the last 25 years based on data from the Public Procurement Service(PPS), Korea Price Research Center and the Landscaping Tree Association(LTA)(hereinafter, officially announcing agencies and organizations) which are major references used when landscape planting is decided. The prices of azalea cultivars announced by the official announcing agencies and organizations have moved in similar patterns over the past 25 years because the prices of azalea cultivars announced by the LTA were referred to by other official announcing agencies and organizations when they officially announced the prices of azalea cultivars. The PPS set lower officially fixed prices of azalea cultivars compared to other official announcing agencies and organizations, and the reason for this is considered to be the intention of the PPS to suppress landscape tree price increases because of the government's policies to suppress price increases. The prices of azalea cultivars seem to change rapidly due to the imbalance between the demand and supply of azalea cultivars rather than the effects of consumer price fluctuation rates because the production periods of azalea cultivars are shorter when compared to other landscape trees. The prices of azalea cultivars from the official announcing agencies and organizations have been set higher than the prices in actual transactions. The reason for this is considered to be the intention of the official announcing agencies and organizations to allow landscaping companies to cover defect costs resulting from the practice of subcontracting planting work and secure profits of subcontractors for planting work. The official announcing agencies and organizations have simply announced prices of 5~8 main azalea cultivars that have been used in the past. The names of azalea cultivars being cultivated and criteria for classification have not been clear; thus, landscape designers have not written clear names of azalea cultivars to be cultivated on planting drawings as practice and landscapers planted those azalea cultivars which could be easily obtained. Therefore, it is assumed that there has been no demand for new azalea cultivars. Thus, the vicious circle in which the prices of only those azalea cultivars that were produced in the past have been announced is repeated.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.7 no.1
• /
• pp.16-21
• /
• 2019

This study has its aim to judge both applicability and suitability of recycling of waste soil for the use of farmland amelioration and low-lying farmland reclamation through growth and development experiment and component analysis. As results of physical characteristic evaluation on recycling of waste soil, the classification based on unified soil classification system has investigated as SW and SP affiliation and soil classification has appeared to be a loamy sand. As results of chemical component analysis, pH has appeared to be 7.0~8.4 which is relatively higher than general soil, however, heavy metal has investigated within the 1 region's standard value of soil pollution standards. As results of germination experiment, when using it by mixing recycling soil less than 75%, there is no significant influence on germination, and in the growth and development experiment, when using horticultural bed soil which is mixed with less than 40% of recycling of waste soil, it has confirmed that there is no significance difference with general soil. In case of farmland, the growth disorder of recycling of waste soil rate no more than 40% has shown that it has relatively small influences, and in case of using it by mixing with agricultural soil, it has evaluated to require concrete review of factors which may restrict growth condition including nutrition and pH.

• Korean Journal of Environment and Ecology
• /
• v.29 no.6
• /
• pp.907-916
• /
• 2015

The purpose of this study was to identify characteristics of vegetation structure, vegetation succession, and species diversity of artificially planted Chamaecyparis obtusa (CO) stands. The study was carried out by performing vegetation survey for eight CO stands located in Jeollanam-do Province, Korea. Analysis on vegetation classification and ordinations of the stands was conducted using the data from the vegetation survey, and as a result, the stands were classified into five types of communities. Community I showed a considerably lower index of species diversity when compared to other communities because the canopy of the dominant CO was so highly dense that the low-height vegetation was not able to develop or the low-height vegetation almost disappeared due to elimination of weed trees. Meanwhile, the Community II - IV had relatively higher indices of species diversity because various native tree species mixed with the low-height vegetation and competed with each other in the understory and shrub layers to some degree of stability or in their early stage of vegetation development. Community V, lastly, showed higher use intensity as a recreational forest, thus developing simpler vegetation structure on account of artificial intervention. There was positive correlation between photosynthetically active radiation entering the forest floor, number of observed species and index of species diversity. Such characteristics of vegetation structure in CO stands are closely associated with forest management and prescription for planting reforestation, thinning, and brush cutting in the past. There was a slight difference in vegetation structure and species diversity by communities, based on rotation time of the vegetational succession, process of disturbance frequency and disturbance, development, and maturity by planting CO stands. However, when compared to natural forests, the CO stands showed simpler vegetation structure. Because artificial forests are vulnerable in ecosystem service with lower species diversity, a drive for ecological management is needed for such forests to change into healthy ecosystems that can display functions of public benefit.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.3
• /
• pp.154-158
• /
• 2011

This research was carried out to compare the standard of estimated unit power and material in landscape architecture construction between Korea and Japan. It has also been done to offer a practical and reasonable information to Korea landscape architecture industry. The research results are as follows. First, both Korea and Japan's standard of estimated unit power and material in landscape architecture construction are part of civil construction. Second, Korea's detailed type of construction is centered on plant's type and size while Japan's centered on architectural construction. Third, Korea's standard of estimated unit power and material are composed of workforce construction, mechanical construction and addition of soil. On the other hand, Japan's estimated unit power and material are composed of workforce construction, time of transportation, date of transportation. Fourth, the planting specification of Korea seems to be more in detail than that of Japan, Japan's showing a wider implication. Fifth, when comparing the information regarding standard of estimated unit power and material between Japan and Korea, transportation, independent stalking for plant, soil for landscape architecture is difference between the two countries. On the base of this research results, Korea's standard of estimated unit power and material in planning construction should be more elastic in its implication and independent standard of estimated unit power and material in landscape architecture construction. Also, examination of transportation, independent skating for plant and soil for landscape architecture should be done in order for better improvements.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.20 no.1
• /
• pp.39-52
• /
• 1992

In order to make plan for landscape construction by ecological methods in Yukong R & D Complex site, environmental factors and structure of plant community were investigated and analyzed around Yukong R & D Complex site of Daeduk. The result of this study were as follows: 1. In the result by the classification of TWINSPAN and ordination (DCA) techniques for analysing of plant community structure, thirty plant community structure, thirty plots were divided into four groups according to soil moisture and succession trends were seem to be from the development of subsidiary vegetation through Pinus densiflora, Quercus spp., Robinia psudoacasia community to Q. acutissima community. So this result was proposed to validity of vegetation introduction for planning of ecological landscape construction in studied site. 2. On the analysis of environmental factors by ordination techeniques, the plant community were divided by soil moisture. Soilcondition will be fertilized by introduction of broad-leaved tree and the development of succession trends from the present state of plant community to Q. acutissima community. 3. The problems of horiticultural places happened to studied site, so horiticultural places for ecological landscape construction was proposed planting techniques that were considered to soil suitability, economical efficiency, native species and wildlife. 4. If we attempt to ecological landscape designs on natural systems and use natural processes to achieve desired end-points, we are more likely to produce self-sustaining solutions.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1397-1399
• /
• 2003

When and Where, What kind of agricultural products will be produced and provided for the market? It is a commercial requirement, and also an academic questions to remote sensing technology. Crop physiology analysis and growth monitoring are important elements for precision agriculture management. Remote sensing technology supplies us more selections and available spaces in this dynamic change study by producing images of different spatial, spectral and temporal resolutions. Especially, the hyperspectral remote sensing should do play a key role in crop growth investigation at national, regional and global scales. In the past five years, Chinese academy of sciences and Japan NTT-DATA have made great efforts to establish a prototype information service system to dynamically survey the vegetable planting situation in Nagano area of Japan mainly based on remote sensing data. For such concern, a flexible and light-duty flight system and some practical data processing system and some necessary background information should be rationally made together. In addition, some studies are also important, such as quick pre-processing for hyperspectral data, Multi-temporal vegetation index analysis, hyperspectral image classification in support of GIS data, etc. In this paper, several spectral data analysis models and a designed airborne platform are provided and discussed here.