• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1046-1052
• /
• 2021

Artificial intelligence is being applied in various industrial fields to the development of the fourth industry and the construction of high-performance computing environments. In the medical field, deep learning learning such as cancer, COVID-19, and bone age measurement was performed using medical images such as X-Ray, MRI, and PET and clinical data. In addition, ICT medical fusion technology is being researched by applying smart medical devices, IoT devices and deep learning algorithms. Among these techniques, medical image-based deep learning learning requires accurate finding of medical image biomarkers, minimal loss rate and high accuracy. Therefore, in this paper, we would like to compare and analyze the performance of the Cross-Entropy function used in the image classification algorithm of the loss function that derives the loss rate in the chest X-Ray image-based deep learning learning process.

• Korean Journal of Radiology
• /
• v.20 no.5
• /
• pp.801-811
• /
• 2019

Objective: To determine whether diffusion kurtosis imaging (DKI) is effective in monitoring tumor response to neoadjuvant chemotherapy in patients with osteosarcoma. Materials and Methods: Twenty-nine osteosarcoma patients (20 men and 9 women; mean age, 17.6 ± 7.8 years) who had undergone magnetic resonance imaging (MRI) and DKI before and after neoadjuvant chemotherapy were included. Tumor volume, apparent diffusion coefficient (ADC), mean diffusivity (MD), mean kurtosis (MK), and change ratio (ΔX) between pre-and post-treatment were calculated. Based on histologic response, the patients were divided into those with good response (≥ 90% necrosis, n = 12) and those with poor response (< 90% necrosis, n = 17). Several MRI parameters between the groups were compared using Student's t test. The correlation between image indexes and tumor necrosis was determined using Pearson's correlation, and diagnostic performance was compared using receiver operating characteristic curves. Results: In good responders, MD_post, ADC_post, and MK_post values were significantly higher than in poor responders (p < 0.001, p < 0.001, and p = 0.042, respectively). The ΔMD and ΔADC were also significantly higher in good responders than in poor responders (p < 0.001 and p = 0.01, respectively). However, no significant difference was observed in ΔMK (p = 0.092). MD_post and ΔMD showed high correlations with tumor necrosis rate (r = 0.669 and r = 0.622, respectively), and MD_post had higher diagnostic performance than ADC_post (p = 0.037) and MK_post (p = 0.011). Similarly, ΔMD also showed higher diagnostic performance than ΔADC (p = 0.033) and ΔMK (p = 0.037). Conclusion: MD is a promising biomarker for monitoring tumor response to preoperative chemotherapy in patients with osteosarcoma.

• Tuberculosis and Respiratory Diseases
• /
• v.66 no.6
• /
• pp.444-450
• /
• 2009

Background: Biomarkers for cancer have several potential clinical uses, including the following: early cancer detection, monitoring for recurrence prognostication, and risk stratification. However, no biomarker has been shown to have adequate sensitivity and specificity. Many investigators have tried to validate biomarkers for the early detection and recurrence of lung cancer. To evaluate plasma G-CSF as such a biomarker, protein levels were measured and were found to correlate with the clinicopathological features of primary lung tumors. Methods: Between December 2006 and May 2008, 100 patients with histologically-validated primary lung cancer were enrolled into this study. To serve as controls, 127 healthy volunteers were enrolled into this study. Plasma G-CSF levels were measured in lung cancer patients using the sandwich ELISA system (R & D inc.) prior to treatment. Results: The mean plasma G-CSF levels were 12.2$\pm$0.3 pg/mL and 46.0$\pm$3.8 pg/mL (mean$\pm$SE) in the normal and in the cancer groups, respectively. In addition, plasma G-CSF levels were higher in patients with early lung cancer than in healthy volunteers (p<.001). Plasma G-CSF levels were higher in patients who were under 65 years old or smokers. Within the cancer group, plasma G-CSF levels were higher in patients with non small cell lung cancer than in patients with small cell lung cancer (p<.05). Overall, plasma G-CSF levels were shown to increase dependent upon the type of lung cancer diagnsosed. In the order from highest to lowest, the levels of plasma G-CSF tended to decrease in the following order: large cell carcinoma, squamous cell carcinoma, adenocarcinoma, and bronchioloalveolar carcinoma. Plasma G-CSF levels tended to be higher in patients with advanced TNM stage than in localized TNM stage (I, II

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.34 no.2
• /
• pp.176-180
• /
• 2005

This study was conducted to examine effect dietary protein and calcium levels on calcium metabolism of the rat. Weaned 6-week old male rats were divided into 4 groups and were fed experimental diets for six weeks. Experimental groups were HPNC group-high protein normal calcium (protein: 400 g/kg diet, calcium: 0.5%), HPLC group-high protein low calcium (protein: 400 g/kg diet, calcium: 0.1%), NPNC group-normal protein normal calcium (protein: 200 g/diet, calcium: 0.5%), NPLC group-normal protein low calcium (protein: 200 g/diet, calcium: 0.1%). The calcium excretion in urine was higher in high protein group than in normal protein group, and it was highest in HPLC group. The activation of alkaline phophatase had a tendency to low in normal calcium group, and the concentration of parathyroid hormone (PTH) was the lowest in HPLC group. The deoxypyridinoline (DPD) concentration of urine was investigated as the highest in HPLC group and it was significantly lower in HPNC group that consumed normal calcium. The bone density of the femur was the highest in NPNC group and the lowest in NPLC group. As the results of this study, calcium excretion in urine and DPD density were the highest and the bone density was the lowest in HPLC group. It may suggest that the deficiency of calcium causes adversely effect in calcium metabolism upon consuming high protein diet. Therefore, it should be emphasized to consume enough calcium to prevent the hindrance of skeletal metabolism caused by deficiency of calcium upon consuming high protein diet.

• Journal of Veterinary Clinics
• /
• v.23 no.2
• /
• pp.144-148
• /
• 2006

Apoptotic death of articular chondrocytes has been implicated in the pathogenesis of osteoarthritis. Tartrate resistant acid phosphatase (TRAP) has been used for several years as a marker enzyme of bone-resorbing osteoclasts. This study investigated the activity of TRAP in media of apoptotic cell death-induced canine chondrocyte. We exposed canine chondrocyte to capsaicin and the results showed that capsaicin induced cell death in a dose dependent manner. And we measured TRAP activity in media of chondrocyte death induced by capsaicin treatment and the results capsaicin significantly increased the activity of TRAP in media for dose dependent. We also investigated whether the combination treatment with capsaicin and TRAIL enhance apoptotic cell death in canine chondrocyte. We exposed canine chondrocyte to capsaicin for 24 hrs at the indicated dose, and then treated with recombinant TRAIL protein for 24 hrs. TRAIL alone did not induce cell death after 24 hours, but the combined treatment of both induced more cell death compared with capsaicin alone in a dose dependent manner. Also, the combination treatment with capsaicin and TRAIL increased the activity of TRAP in culture media. These results suggest that TRAP can flow out into extracellular after chondrocyte damage, and TRAP may be a successful biomarker for detection of joint disease such as osteoarthritis.

• Tuberculosis and Respiratory Diseases
• /
• v.71 no.3
• /
• pp.195-201
• /
• 2011

Background: Osteopontin (Opn) is recognized as an important adhesive bone matrix protein and a key cytokine involved in immune cell recruitment and tissue repair and remolding. However, serum levels of osteopontin have not been evaluated in patients with chronic obstructive pulmonary disease (COPD). Thus, the aim of this study was to evaluate and compare the serum levels of osteopontin in patients experiencing COPD exacerbations and in patients with stable COPD. Methods: Serum samples were obtained from 22 healthy control subjects, 18 stable COPD patients, and 15 COPD with exacerbation patients. Serum concentrations of osteopontin were measured by the ELISA method. Results: Serum levels of osteopontin were higher in patients with acute exacerbation than with stable COPD and in healthy control subjects ($62.4{\pm}51.9ng/mL$, $36.9{\pm}11.1ng/mL$, $30{\pm}11ng/mL$, test for trend p=0.003). In the patients with COPD exacerbation, the osteopontin levels when the patient was discharged from the hospital tended to decrease compared to those at admission ($45{\pm}52.1ng/mL$, $62.4{\pm}51.9ng/mL$, p=0.160). Osteopontin levels significantly increased according to patient factors, including never-smoker, ex-smoker and current smoker ($23{\pm}5.7ng/mL$, $35.5{\pm}17.6ng/mL$, $58.6{\pm}47.8ng/mL$, test for trend p=0.006). Also, osteopontin levels showed a significantly negative correlation with forced expiratory volume in one second ($FEV_1$%) predicted in healthy controls and stable COPD patients (r=-0.389; p=0.013). C-reactive protein (CRP) was positively correlated with osteopontin levels in patients with COPD exacerbation (r=0.775; p=0.002). Conclusion: The serum levels of osteopontin increased in patients with COPD exacerbation and tended to decrease after clinical improvement. These results suggest the possible role of osteopontin as a biomarker of acute exacerbation of COPD.