• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.189-198
• /
• 2024

Objective: To investigate the prognostic utility of radiomics features extracted from ¹⁸F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL). Materials and Methods: A total of 126 adults with ENKTCL who underwent ¹⁸F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3. Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient's radiomics scores (RadPFS and RadOS). Kaplan-Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell's C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve. Results: Kaplan-Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell's C-index: 0.805 in the validation cohort) and OS (Harrell's C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance. Conclusion: The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.8
• /
• pp.2163-2169
• /
• 2010

G-protein coupled receptors (GPCRs) are involved in a wide variety of physiological processes and are known to be targets for nearly 50% of drugs. The various functions of GPCRs are affected by their cognate ligands which are mainly classified as agonists and antagonists. The purpose of this study is to develop a Bayesian classification model, that can predict a compound as either human GPCR agonist or antagonist. Total 6627 compounds experimentally determined as either GPCR agonists or antagonists covering all the classes of GPCRs were gathered to comprise the dataset. This model distinguishes GPCR agonists from GPCR antagonists by using chemical fingerprint, FCFP_6. The model revealed distinctive structural characteristics between agonistic and antagonistic compounds: in general, 1) GPCR agonists were flexible and had aliphatic amines, and 2) GPCR antagonists had planar groups and aromatic amines. This model showed very good discriminative ability in general, with pretty good discriminant statistics for the training set (accuracy: 90.1%) and a good predictive ability for the test set (accuracy: 89.2%). Also, receiver operating characteristic (ROC) plot showed the area under the curve (AUC) to be 0.957, and Matthew's Correlation Coefficient (MCC) value was 0.803. The quality of our model suggests that it could aid to classify the compounds as either GPCR agonists or antagonists, especially in the early stages of the drug discovery process.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.97-103
• /
• 2001

Hidden Markov Model (HMM) is the most widely used method in speech recognition. In general, HMM parameters are trained to have maximum likelihood (ML) for training data. Although the ML method has good performance, it dose not take account into discrimination to other words. To complement this problem, a word verification method by re-recognition of the recognized word and its similar word using the discriminative function of the two words. To find the similar word, the probability of other words to the HMM is calculated and the word showing the highest probability is selected as the similar word of the mode. To achieve discrimination to each word the weight to each state is appended to the HMM parameter. The weight is calculated by genetic algorithm. The verificator complemented discrimination of each word and reduced the error occurred by similar word. As a result of verification the total error is reduced by about 22%

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1807-1823
• /
• 2016

Local Binary Pattern (LBP) and its variants have powerful discriminative capabilities but most of them just consider each LBP code independently. In this paper, we propose sub oriented histograms of LBP for smoke detection and image classification. We first extract LBP codes from an image, compute the gradient of LBP codes, and then calculate sub oriented histograms to capture spatial relations of LBP codes. Since an LBP code is just a label without any numerical meaning, we use Hamming distance to estimate the gradient of LBP codes instead of Euclidean distance. We propose to use two coordinates systems to compute two orientations, which are quantized into discrete bins. For each pair of the two discrete orientations, we generate a sub LBP code map from the original LBP code map, and compute sub oriented histograms for all sub LBP code maps. Finally, all the sub oriented histograms are concatenated together to form a robust feature vector, which is input into SVM for training and classifying. Experiments show that our approach not only has better performance than existing methods in smoke detection, but also has good performance in texture classification.

• Journal of Digital Convergence
• /
• v.16 no.7
• /
• pp.131-144
• /
• 2018

The purpose of this study is to empirically examine the unethical information sharing by information asymmetry. I will confirm the effect of ethical dilemma, unethical intention and behavior by the information asymmetry. A research method used the structural equations. The analysis showed causal relationship that ethical dilemma and unethical intention and behaviors by the information sharing. In particular, The ethical dilemma by position level showed different from the factor between dilemma and intention. As a result, the organization should manage differently ethical issue according to position level. The contribution in this study has expended an interpretation scope of broken windows theory from social science and explained a discriminative management of the ethical dilemma by position level from the practical view. A Future study should investigate an unethical behavior reduce by information security systems.

• Journal of Society of Preventive Korean Medicine
• /
• v.26 no.2
• /
• pp.37-53
• /
• 2022

Objectives : This study analyzed the concordance between student self-assessment and peer-evaluation in a role play using the Clinical Performance Examination (CPX) scenario developed based on Korean medical syndrome differentiation. Methods : The subjects of this study are first-year-students majoring in Korean Medicine. The role play based on clinical case was performed in the class of Korean Medicine Classics. Feedback on clinical skill competency got through student self-assessment and peer-evaluation, and this study was compared and analyzed of result. Results : A simple comparison of the results of self-assessment and peer-evaluation in the evaluation results of clinical skill competency may appear to be consistent. However, it was not statistically significant. It is necessary to enhance the discriminative ability in the evaluation of clinical skill competency. It will be possible to improve a bit by relatively increasing the weight of the scores on the items that students expect to respond differently among the evaluation items. In addition, in order to dramatically improve the systemicity and reliability of the evaluation of clinical skill competency itself, it is necessary to introduce the Introduction to Clinical Traditional Korean Medicine (ICTKM) course. Conclusions : Student's self-assessment and peer-evaluation as feedback on clinical skill competency are suitable for the purpose of education and training. However, the reliability of the evaluation was not statistically significant.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.3
• /
• pp.47-57
• /
• 2020

This study focuses on the proposition that the qualities and environmental conditions required for exploring entrepreneurial opportunities and realizing entrepreneurial opportunities depend on the types of entrepreneurial opportunities. In particular, this study aims to identify the type of entrepreneurial opportunities for laboratory start-ups, which have recently been gaining policy level attention. If the type of entrepreneurial opportunities for laboratory start-ups is identified as discriminative, appropriate start-up support policies and training programs can be established. For this study, eight major papers were identified among the papers of last 30 years related to the types of entrepreneurial opportunities. After, the classification attributes for each opportunity type were derived. Then, the existing theories of recognition, discovery and creative opportunities were organized, critically reviewed and reorganized. In addition, the substance of laboratory start-ups was verified according to the standardized classification attributes of the revised and reorganized opportunity types and newly classified as 'creative opportunity'. This study also presents networking capabilities and market orientation as examples of the capabilities needed for entrepreneurs of creative opportunity type. The implication of this study is that it makes it easy to discriminate ontological typology of entrepreneurial opportunity, derives important classification attributes, and that it organizes them conceptually. In addition, it critically reconstructs the problems of confusion in the existing typology, and based on this, the type of entrepreneurial opportunities for laboratory start-ups is determined as creative opportunity. These achievements can contribute to the improvement of start-up policies and start-up training programs according to the types of entrepreneurial opportunity and laboratory start-ups in the future, resulting in realization of actual results at the start-up sites.

• The Journal of Industrial Distribution & Business
• /
• v.9 no.10
• /
• pp.39-50
• /
• 2018

Purpose - This study is to propose discriminative management strategies to long-term care facilities based on the empirical analysis after reviewing the effects of social support, perceived by long-term care facility employees, to service orientation. Research design, data, and Methodology - The research model designed social support, job stress, organizational commitment, and service orientation. The survey collected data from 453 customers in a long-term care facility in jeju. The SPSS 18.0 package was used for analysis. Results - First, social support for long-term care facility employees has a negative(-) effect to job stress. Test results, social support factors except appraisal support had a negative impact on job stress. Second, social support has a positive(+) effect to organizational commitment. Test results, informational support, tangible support and appraisal support had significant effects on organizational commitment. However, emotional support had a positive impact on affective commitment and normative commitment. Third, social support has a positive(+) effect to service orientation. Test results had a positive impact. Fourth, job stress has a negative(-) effect to organizational commitment. In the test results, employee's continuance commitment and normative commitment had significant negative effects in job stress. However, affective commitment had no significant impact. Fifth, job stress has a negative(-) effect to service orientation. Test results showed a negative impact. Conclusions - The study implies the following. First, that there should be a change in the social perception of long-term care facilities. 'Long-Term Care Insurance for The Elderly' was enacted to emphasize this responsibility for the elderly problems as a new system. Enactment of this Act was expected to improve the quality of life of the people by stabilizing the elderly life and reducing the burden of families. Therefore, long-term care facility system should be as efficient as possible for making plans for systematic and organizational support. Second, the efforts of facility managers to minimize job stress of employees is necessary. Accordingly, performing spontaneous work is required for a comfortable working environment and management. Third, the systematic education and training to employees for service oriented behavior of the facility will be required in the long term.

• Journal of Radiation Protection and Research
• /
• v.47 no.4
• /
• pp.237-245
• /
• 2022

Background: The current study reports measurements of activity concentrations of radon (²²⁰Rn) and thoron (²²⁰Rn) in dwellings, followed by inhalation dose assessment of the public, and then by the development of regulation and the national radon action plan (NRAP) in Cameroon. Materials and Methods: Radon, thoron, and thoron progeny measurements were carried out from 2014 to 2017 using radon-thoron discriminative detectors (commercially RADUET) in 450 dwellings and thoron progeny monitors in 350 dwellings. From 2019 to 2020, radon track detectors (commercially RADTRAK) were deployed in 1,400 dwellings. It was found that activity concentrations of radon range in 1,850 houses from 10 to 2,620 Bq/㎥ with a geometric mean of 76 Bq/㎥. Results and Discussion: Activity concentrations of thoron range from 20 to 700 Bq/㎥ with a geometric mean of 107 Bq/㎥. Thoron equilibrium factor ranges from 0.01 to 0.6, with an arithmetic mean of 0.09 that is higher than the default value of 0.02 given by UNSCEAR. On average, 49%, 9%, and 2% of all surveyed houses have radon concentrations above 100, 200, and 300 Bq/㎥, respectively. The average contribution of thoron to the inhalation dose due to radon and thoron exposure is about 40%. Thus, thoron cannot be neglected in dose assessment to avoid biased results in radio-epidemiological studies. Only radon was considered in the drafted regulation and in the NRAP adopted in October 2020. Reference levels of 300 Bq/㎥ and 1,000 Bq/㎥ were recommended for dwellings and workplaces. Conclusion: Priority actions for the coming years include the following: radon risk mapping, promotion of a protection policy against radon in buildings, integration of the radon prevention and mitigation into the training of construction specialists, mitigation of dwellings and workplaces with high radon levels, increased public awareness of the health risks associated with radon, and development of programs on the scientific and technical aspects.