• Journal of IKEEE
• /
• v.11 no.2
• /
• pp.89-94
• /
• 2007

This paper is a study on continuous speech recognition in the Korean language using HMM-based models with continuous density functions. Here, we propose the most efficient method of continuous speech recognition for the Korean language under the condition of a continuous HMM model with 2 to 44 density functions. Two voice models were used CI-Model that uses 36 uni-phones and CD-Model that uses 3,000 tri-phones. Language model was based on N-gram. Using these models, 500 sentences and 6,486 words under speaker-independent condition were processed. In the case of the CI-Model, the maximum word recognition rate was 94.4% and sentence recognition rate was 64.6%. For the CD-Model, word recognition rate was 98.2% and sentence recognition rate was 73.6%. The recognition rate of CD-Model we obtained was stable.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.9
• /
• pp.4627-4630
• /
• 2012

Purpose: Methylenetetrahydrofolate reductase (MTHFR) gene polymorphisms have been reported to be associated with pancreatic cancer, but the published studies have yielded inconsistent results. This study assessed the relationship between MTHFR gene polymorphisms and the risk for pancreatic cancer using a meta-analysis approach. Methods:A search of Google scholar, PubMed, Cochrane Library and CNKI databases before April 2012 was performed, and then associations of the MTHFR polymorphisms with pancreatic cancer risk were summarized. The association was assessed by odds ratios (ORs) with 95% confidence intervals (CIs). Publication bias was also calculated. Results: Four relative studies on MTHFR gene polymorphisms (C667T and A1298C) were included in this meta-analysis. Overall, C667T (TT vs. CC:OR=1.61,95%CI=0.78-3.34; TT vs. CT: OR=1.41,95%CI=0.88-2.25; Dominant model:OR=0.68,95%CI=0.40-1.17; Recessive model: OR=0.82,95%CI=0.52-1.30) and A1298C (CC vs. AA:OR=1.01,95%CI=0.47-2.17; CC vs. AC: OR=0.99,95%CI=0.46-2.14; Dominant model:OR=1.01, 95%CI=0.47-2.20; Recessive model: OR=1.01,95%CI=0.80-1.26) did not increase pancreatic cancer risk. Conclusions: This meta-analysis indicated that MTHFR polymorphisms (C667T and A1298C) are not associated with pancreatic cancer risk.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.18
• /
• pp.7515-7520
• /
• 2014

Many studies have indicated possible associations between a polymorphism of adiponectin receptor 1 (ADIPOR1) rs1342387 and risk of cancer, but contradictory results have been reported. The main aim of this study was to draw a reliable conclusion about the relationship between the rs1342387 polymorphism and cancer incidence, by conducting a literature search of Pubmed, Embase, Wanfang and Cochrane libraries. Eleven studies including 3, 738 cases and 4, 748 controls were identified in this meta-analysis. The ADIPOR1 rs1342387 polymorphism was associated with risk of colorectal cancer for all genetic comparison models (GG vs AA, OR: 1.44, 95%CI: 1.21-1.70; G carriers vs A carriers, OR: 1.23, 95%CI: 1.11-1.36; dominant model, OR: 1.28, 95%CI: 1.10-1.49 and recessive model, OR: 1.31, 95%CI: 1.12-1.55). Stratified by ethnicity, the rs1342387 polymorphism was significantly associated with risk of colorectal cancer in Asian ancestry for all genetic comparison models (GG vs AA, OR: 1.56, 95%CI: 1.26-1.92; G carriers vs. A carriers OR: 1.30, 95%CI: 1.18-1.43; dominant model OR: 1.31, 95%CI: 1.08-1.60 and recessive model OR: 1.44, 95%CI: 1.26-1.64), but not in Caucasian or mixed (Caucasian mainly) groups. In summary, the ADIPOR1 rs1342387 polymorphism is significantly associated with risk of colorectal cancer among individuals of Asian ancestry.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.15
• /
• pp.6181-6186
• /
• 2014

This meta-analysis was conducted to examine whether the genotype status of Val158Met polymorphism in catechol-O-methyltransferase (COMT) is associated with endometrial and ovarian cancer risk. Eligible studies were identified by searching several databases for relevant reports published before January 1, 2014. Pooled odds ratios (ORs) were appropriately derived from fixed-effects or random-effects models. In total, 15 studies (1,293 cases and 2,647 controls for ovarian cancer and 2,174 cases and 2,699 controls for endometrial cancer) were included in the present meta-analysis. When all studies were pooled into the meta-analysis, there was no evidence for significant association between COMT Val158Met polymorphism and ovarian cancer risk (Val/Met versus Val/Val: OR=0.91, 95% CI=0.76-1.08; Met/Met versus Val/Val: OR=0.90, 95% CI=0.73-1.10; dominant model: OR=0.90, 95% CI=0.77-1.06; recessive model: OR=0.95, 95% CI=0.80-1.13). Similarly, no associations were found in all comparisons for endometrial cancer (Val/Met versus Val/Val: OR 0.97, 95% CI=0.77-1.21; Met/Met versus Val/Val: OR=1.02, 95% CI=0.73-1.42; dominant model: OR=0.98, 95% CI=0.77-1.25; recessive model: OR=1.02, 95% CI=0.87-1.20). In the subgroup analyses by source of control and ethnicity, no significant associations were found in any subgroup of population. This meta-analysis strongly suggests that COMT Val158Met polymorphism is not associated with increased endometrial and ovarian cancer risk.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.5
• /
• pp.2249-2252
• /
• 2012

Objective: Methylenetetrahydrofolate reductase (MTHFR) gene polymorphisms have been reported to be associated with pancreatic cancer, but the published studies had yielded inconsistent results.We therefore performed the present meta-analysis. Methods: A search of Google scholar, PubMed, Cochrane Library and CNKI databases before April 2012 was conducted to summarize associations of MTHFR polymorphisms with pancreatic cancer risk. Assessment was with odds ratios (ORs) and 95% confidence intervals (CIs). Publication bias were also calculated. Results: Four relative studies on MTHFR gene polymorphisms (C667T and A1298C) were involved in this meta-analysis. Overall, C667T(TT vs. CC : OR = 1.61, 95%CI = 0.78 - 3.34; TT vs. CT : OR = 1.41, 95%CI = 0.88-2.25; dominant model: OR = 0.68, 95%CI = 0.40-1.17; recessive model: OR = 0.82, 95%CI = 0.52-1.30) and A1298C(CC vs. AA:OR=1.01, 95%CI=0.47-2.17; CC vs. AC: OR=0.99,95%CI=0.46-2.14; dominant model: OR=1.01, 95%CI = 0.47-2.20; recessive model: OR = 1.01, 95%CI = 0.80-1.26) did not increase pancreatic cancer risk. Conclusion: This meta-analysis indicated that MTHFR polymorphisms (C667T and A1298C) were not associated with pancreatic cancer risk.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.2
• /
• pp.579-583
• /
• 2012

Background: The SULT1A1 Arg213His polymorphism is reported to be associated with lung cancer risk. However, this relationship remains controversial. For better understanding a meta-analysis was therefore performed. Methods: An extensive search was performed to identify all case-control studies investigating association between SULT1A1 Arg213His polymorphism and lung cancer risk. The strength was assessed by odds ratio (OR) with the corresponding 95% confidence interval (95%CI). Results: A total of five publications covering 1,669 cases and 1,890 controls were included in this meta-analysis. No significant association between SULT1A1 Arg213His polymorphism and lung cancer risk was observed in overall comparisons in all genetic models (dominant model: OR=1.33, 95%CI=1.00-1.76, P=0.05; additive model: OR=1.30, 95%CI=0.93-1.81, P=0.12; recessive model: OR=1.21, 95%CI=0.89-1.66, P=0.23). However, on subgroup analysis, an elevated risk in mixed populations with variant His allele was revealed in the dominant model (OR=1.66, 95% CI=1.06-2.62, P=0.03). Furthermore, the SULT1A1 Arg213His polymorphism was associated with an increased risk of lung cancer in both females and males in the dominant model (females: OR=1.72, 95%CI=1.29-2.27, P=0.00; males: OR=1.46, 95%CI=1.19-1.78, P=0.00). No significant association between this polymorphism and different smoking status (smokers and non-smokers) and the other ethnicities (Asians and Caucasians) was shown. Conclusions: The results of this meta-analysis indicate that the SULT1A1 Arg213His polymorphism is not associated with lung cancer risk in Asians and Caucasians, but possible elevation for genotype (GA/AA) in mixed populations and males and females needs further investigation.

• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.4
• /
• pp.2269-2272
• /
• 2013

Matrix metalloproteinases (MMPs) degrade various components of the extracellular matrix and functional polymorphisms in encoding genes may contribute to genetic susceptibility to many cancers. Up to now, associations between MMP-7 (-181A>G) and digestive system cancer risk have remained inconclusive. To better understand the role of the MMP-7 (-181A>G) genotype in digestive cancer development, we conducted this comprehensive meta-analysis encompassing 3,518 cases and 4,596 controls. Overall, the MMP-7 (-181A>G) polymorphism was associated with higher digestive system cancer risk on homozygote comparison (GG vs. AA, OR=1.21, 95% CI = 1.12-1.60) and in a dominant model (GG/GA vs. AA, OR=1.16, 95% CI =1.03-1.46). On subgroup analysis, this polymorphism was significantly linked to higher risks for gastric cancer (GG vs. AA, OR=1.22, 95% CI = 1.02-1.46; GA vs. AA, OR=1.82, 95% CI =1.16-2.87; GG/GA vs. AA, OR=1.13, 95% CI =1.01-1.27; GG vs. GA/AA, OR= 1.25, 95% CI = 1.06-2.39. We also observed increased susceptibility to colorectal cancer and esophageal SCC in both homozygote (OR = 1.13, 95% CI = 1.06-1.26) and heterozygote comparisons (OR = 1.45, 95% CI = 1.11-1.91). In the stratified analysis by controls, significant effects were only observed in population-based studies (GA vs. AA, OR=1.16, 95% CI=1.08-1.50; GA/AA vs. GG, OR=1.10, 95% CI=1.01-1.72). According to the source of ethnicity, a significantly increased risk was found among Asian populations in the homozygote model (GG vs. AA, OR=1.40, 95% CI=1.12-1.69), heterozygote model (GA vs. AA, OR=1.26, 95% CI=1.02-1.51), and dominant model (GG/GA vs. AA, OR=1.18, 95% CI=1.08-1.55). Our findings suggest that the MMP-7 (-181A>G) polymorphism may be a risk factor for digestive system cancer, especially among Asian populations.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.16
• /
• pp.6709-6714
• /
• 2014

The rs2273535 polymorphism in the AURKA gene had proven to be associated with breast carcinoma susceptibility. Nevertheless, the results of different studies remain contradictory. A meta-analysis covering 28, 789 subjects from eleven different studies was here carried out in order to investigate the association in detail. The random effects model was used to analyze the pooled odds ratios (ORs) and their corresponding 95% confidence intervals (95% CIs). A significant relationship between the rs2273535 polymorphism and breast tumors was found in an allelic genetic model (OR: 1.076, 95% CI: 1.004-1.153, p=0.040, $P_{heterogeneity}$=0.002). No significant association was detected in a homozygote model (OR: 1.186, 95% CI: 0.990-1.423, P=0.065, $P_{heterogeneity}$=0.002), a heterozygote model (OR: 1.016, 95% CI: 0.959-1.076, p=0.064, $P_{heterogeneity}$=0.000), a dominant genetic model (OR: 1.147, 95% CI: 0.992-1.325, p=0.217, $P_{heterogeneity}$=0.294) and a recessive genetic model (OR: 1.093, 95% CI: 0.878-1.361, p=0.425, $P_{heterogeneity}$=0.707). A significant relationship between the rs2273535 polymorphism in the AURKA gene and breast tumor in Asian group was found in an allelic genetic model (OR: 1.124, 95% CI: 1.003-1.29, p=0.044, $P_{heterogeneity}$=0.034), a homozygote model (OR: 1.229, 95% CI: 1.038-1.455, p=0.016, $P_{heterogeneity}$=0.266) and a recessive genetic model (OR: 1.227, 95% CI: 1.001-1.504, p=0.049, $P_{heterogeneity}$=0.006). A significant association was thus observed between the rs2273535 polymorphism in the AURKA gene and breast cancer risk. Individuals with the rs2273535 polymorphism in the AURKA gene have a higher risk of breast cancer in Asian populations, but not in Caucasians.

• Journal of Preventive Veterinary Medicine
• /
• v.41 no.3
• /
• pp.129-132
• /
• 2017

The current study identified risk factors associated with porcine circovirus type 2 (PCV2) infection on pig farms in the Republic of Korea using a multinomial logistic regression model to evaluate the PCV2 infection status of pigs at different growth stages. Compulsory disinfection of visitors (odds ratio [OR]: 0.019, 95% confidence interval [CI]: <0.001-0.378, p=0.0095), compulsory registration of visitors (OR: 0.002, 95% CI: <0.001-0.184, p=0.0070), regular blood testing (OR: 0.012, 95% CI: <0.001-0.157, p=0.0007), and running on-farm biosecurity learning programs for workers (OR: 0.156, 95% CI: 0.040-0.604, p=0.0072 and OR: 0.201, 95% CI: 0.055-0.737, p=0.0155, respectively) were identified as factors which could reduce the risk of PCV2 infection. However, visitation by a regular veterinarian (OR: 32.733, 95% CI: 3.768-284.327, p=0.0016) was associated with PCV2 infection.