• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.505-516
• /
• 2022

Objective: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms. Materials and Methods: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated. Results: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001). Conclusion: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.10
• /
• pp.5965-5972
• /
• 2013

PIN1 is one member of the parvulin PPIase family. By controlling Pro-directed phosphorylation, PIN1 plays an important role in cell transformation and oncogenesis. There are many polymorphisms in the PIN1 gene, including rs2233678 and rs2233679 affecting the PIN1 promoter. Recently, a number of case-control studies were conducted to investigate the association between PIN1 gene rs2233678 and rs2233679 polymorphism and cancer risk. However, published data are still conflicting. In this paper, we summarized data for 5,427 cancer cases and 5,469 controls from 9 studies and attempted to assess the susceptibility of PIN1 gene polymorphism to cancers by a synthetic meta-analysis. Odds ratios (ORs) with 95% confidence intervals (CIs) were estimated to assess the relationship. All analyses were performed using Stata software. Our results suggested that rs2233678 represented a protective factor in overall analysis (CC vs GG: OR= 0.697, 95%CI: 0.498-0.976; CG vs GG: OR=0.701, 95%CI: 0.572-0.858; Dominant model: OR= 0.707, 95%CI: 0.590-0.847; C allele vs G allele: OR=0.734, 95%CI: 0.623-0.867) and especially for squamous cell carcinoma of the head and neck, lung cancer and breast cancer in Asians and Caucasians. The rs2233679 polymorphism was significantly associated with decreased cancer risk in overall analysis (CT vs CC: OR=0.893, 95%CI=0.812-0.981; Dominant model: OR=0.893, 95%CI=0.816-0.976; T allele vs C allele; OR=0.947, 95%CI=0.896-1.000) and especially in Asians. In conclusion, our meta-analysis suggested that -842G>C (rs2233678) and -667C>T (rs2233679) may contribute to genetic susceptibility for cancer risks. Further prospective research with larger numbers of worldwide participants is warranted to draw comprehensive and firm conclusions.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.9
• /
• pp.3639-3644
• /
• 2015

Oral, cervical and breast cancers, which are either preventable and/or amenable to early detection and treatment, are the leading causes of cancer-related morbidity and mortality in India. In this paper, we describe implementation science research priorities to catalyze the prevention and control of these cancers in India. Research priorities were organized using a framework based on the implementation science literature and the World Health Organization's definition of health systems. They addressed both community-level as well as health systems-level issues. Community-level or "pull" priorities included the need to identify effective strategies to raise public awareness and understanding of cancer prevention, monitor knowledge levels, and address fear and stigma. Health systems-level or "push" and "infrastructure" priorities included dissemination of evidence-based practices, testing of point-of-care technologies for screening and diagnosis, identification of appropriate service delivery and financing models, and assessment of strategies to enhance the health workforce. Given the extent of available evidence, it is critical that cancer prevention and treatment efforts in India are accelerated. Implementation science research can generate critical insights and evidence to inform this acceleration.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1314-1323
• /
• 1999

컴퓨터의 사용이 일반화됨에 따라 데이타를 생성하고 수집하는 것이 용이해졌다. 이에 따라 데이타로부터 자동적으로 유용한 지식을 얻는 기술이 필요하게 되었다. 데이타 마이닝에서 얻어진 지식은 정확성과 이해성을 충족해야 한다. 본 논문에서는 데이타 마이닝을 위하여 퍼지 결정트리에 기반한 효율적인 퍼지 규칙을 생성하는 알고리즘을 제안한다. 퍼지 결정트리는 ID3와 C4.5의 이해성과 퍼지이론의 추론과 표현력을 결합한 방법이다. 특히, 퍼지 규칙은 속성 축에 평행하게 판단 경계선을 결정하는 방법으로는 어려운 속성 축에 평행하지 않는 경계선을 갖는 패턴을 효율적으로 분류한다. 제안된 알고리즘은 첫째, 각 속성 데이타의 히스토그램 분석을 통해 적절한 소속함수를 생성한다. 둘째, 주어진 소속함수를 바탕으로 ID3와 C4.5와 유사한 방법으로 퍼지 결정트리를 생성한다. 또한, 유전자 알고리즘을 이용하여 소속함수를 조율한다. IRIS 데이타, Wisconsin breast cancer 데이타, credit screening 데이타 등 벤치마크 데이타들에 대한 실험 결과 제안된 방법이 C4.5 방법을 포함한 다른 방법보다 성능과 규칙의 이해성에서 보다 효율적임을 보인다.Abstract With an extended use of computers, we can easily generate and collect data. There is a need to acquire useful knowledge from data automatically. In data mining the acquired knowledge needs to be both accurate and comprehensible. In this paper, we propose an efficient fuzzy rule generation algorithm based on fuzzy decision tree for data mining. We combine the comprehensibility of rules generated based on decision tree such as ID3 and C4.5 and the expressive power of fuzzy sets. Particularly, fuzzy rules allow us to effectively classify patterns of non-axis-parallel decision boundaries, which are difficult to do using attribute-based classification methods.In our algorithm we first determine an appropriate set of membership functions for each attribute of data using histogram analysis. Given a set of membership functions then we construct a fuzzy decision tree in a similar way to that of ID3 and C4.5. We also apply genetic algorithm to tune the initial set of membership functions. We have experimented our algorithm with several benchmark data sets including the IRIS data, the Wisconsin breast cancer data, and the credit screening data. The experiment results show that our method is more efficient in performance and comprehensibility of rules compared with other methods including C4.5.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.16
• /
• pp.7189-7193
• /
• 2015

Background: Cancer is a leading cause of death throughout the world. Increasing life expectancy and aging population are important factors for increasing cancer incidences in developing countries. National programs are essential for prevention and control of cancer in any society. This study aimed to investigate cancer epidemiology and trends in the province of Hamadan, located in Northwest Iran. Materials and Methods: This analytical study was carried out based on cancer registry data from 2004 to 2009 in the province of Hamadan, analyzed using STATA (version 12) software for descriptive tests and Join point 4.1.1.1 software for analytical tests. Results: There were 7,767 registered cases of cancer during the 6 years studied. Of the total cases registered, 59.1% (4,592 cases) involved men and 40.9% (3,175 cases) occurred in women. Age-standardized incidence rates (ASR) increased from 72.9 to 132.0 in males and 48.2 to 115.0 in females during the 6 years of the study (p<0.001). The most common cancers were skin, stomach, breast, bladder, and leukemia. In women, teh most common were breast, skin, stomach, colorectal, and leukemia, in that order, and in men skin, stomach, bladder, leukemia, and prostate cancers. Conclusions: The cancer incidence is greater in men that women in this region but with increasing trends in both sexes. Planning regarding education in prevention of exposure to risk factors and control strategies is required to decrease the incident cases. Screening programs for common cancers in older age groups might be helpful to reduce the disease impact.

• The Korean Journal of Food And Nutrition
• /
• v.15 no.4
• /
• pp.307-313
• /
• 2002

The primary objective of these studies was to screen the materials showing inhibitions of HMG-CoA reductase in vitro. The secondary objective was to determine the effect of garlic, lovastatin and copper on cholesterol concentrations in plasma, liver and breast tissues in pullets. The degree of inhibition of the selective samples on HMG-CoA reductase activity was determined in vitro. The inhibition ratios of water soluble garlic extracts, lovastatin (methanol extracts) and copper to HMG-CoA reductase activity were 51.3%, 87.5%, and 82.0%, respectively. Control diet (basal diet) and experimental diets, garlic powder (3% in diet), lovastatin (300mg/Kg of diet) and copper (200mg/Kg of diet) were fed to pullets in order to investigate the changes of cholesterol concentration in plasma and tissues. Total cholesterol, HDL- and LDL-cholesterol in blood plasma were significantly reduced in pullets fed diet containing 3% garlic powder. However, copper significantly increased total cholesterol compared to control and lovastatin did not affect plasma cholesterol concentration. Total cholesterol and triglyceride of liver and breast tissues in pullets were not affected by adding the cholesterol-lowering materials to diets. The data suggests that it is not easy for HMG-CoA reductase inhibitors to reduce cholesterol levels in body due to complication of cholesterol metabolism. However, garlic administration can lower the levels of plasma cholesterol in pullets.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.8
• /
• pp.3595-3600
• /
• 2012

Objective: The objective of this study was to determine the practice and barriers of mammography and associated factors among Malaysian women in the general population. Methodology: A cross-sectional study was conducted among 200 women in Shah Alam, Selangor; Malaysia. The questionnaire contained 27 questions and was comprised of two sections; socio-demographic characteristics and practices, knowledge and barriers of mammography. All the data were analyzed using the Statistical Package for the Social Sciences (SPSS) 13.0. Results: Of the 200 Malaysian women who participated in this study, the majority were under the age of 50 years (65.5%), Malay (86%), and married (94.5%). Regarding any family history of cancer in general, the majority of the participants had none (78%). However, some did report a close relative with breast cancer (16.5%). While the majority of them knew about mammography (68%), 15% had had a mammogram once in their life and only 2% had the procedure every two or three years. Univariate analysis showed that age, family history of cancer, family history of breast cancer, regular supplement intake, regular medical check-up and knowledge about mammogram were significantly associated with mammogram practice among the general population (p=0.007, p=0.043, P=0.015, p=0.01, p=0.001, p<0.001; respectively). Multivariate analysis using multiple linear regression test showed that age, regular medical check-up and knowledge about mammography testing were statistically associated with the practice of mammography among the general population in Malaysia (p=0.035, p=0.015 and p<0.001; respectively). Lack of time, lack of knowledge, not knowing where to go for the test and a fear of the test result were the most important barriers (42.5%, 32%, 21%, 20%; respectively). Conclusion: The practice of mammogram screening is low among Malaysian women.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.31 no.4
• /
• pp.128-146
• /
• 2018

Objectives: This study was performed to analyze the prescriptions of Korean herbal medicine which had been commonly used during postpartum period. Methods: We searched literature on postpartum cares with Korean Herbal medicine in 4 domestic search engines. After that, we conducted eligibility screening based on inclusion and exclusion criteria. Results: 1. We selected total 48 studies. There were 40 clinical studies (25 case reports and 15 case series) and 8 animal experimental studies. 2. Of the 40 clinical studies, other treatments were used together with herbal medicine : acupuncture (28), chuna manipulation (3), and pharmacopuncture (5). 3. Of the 25 case reports, the most common symptoms were musculoskeletal symptoms (8), followed by mental disorders including postpartum depression (5). Various prescriptions of herbal medicine were used depending on the diseases or symptoms. 4. In 15 case series, 665 subjects in 11 case series had taken Saenghwa-tang-gagam within 1~2 weeks after childbirth, and the average duration of Saenghwa-tang-gagam administration were $9{\pm}4.97$ days. 498 subjects in 9 studies were breast-feeding, and there were no side effects reported. 5. All experimental studies were about the recovery, the immunity and the breast-feeding associated puerperal characteristics. Also, 3 studies used Saenghwa-tang as an intervention. Conclusions: Saenghwa-tang can be commonly used for the purpose of prevention and care of the postpartum symptoms within the first 1~2 weeks after childbirth for 10 days. Also, various prescriptions of herbal medicine may be used depending on the diseases or symptoms, and can be conducted with other treatments like acupuncture, cupping, moxibustion, pharmacopuncture and chuna manipulation.

• Genomics & Informatics
• /
• v.19 no.4
• /
• pp.39.1-39.8
• /
• 2021

Tamoxifen (TAM) is an anticancer drug used to treat estrogen receptor (ER)-positive breast cancer. However, its ER-independent cytotoxic and antifungal activities have prompted debates on its mechanism of action. To achieve a better understanding of the ER-independent antifungal action mechanisms of TAM, we systematically identified TAM-sensitive genes through microarray screening of the heterozygous gene deletion library in fission yeast (Schizosaccharomyces pombe). Secondary confirmation was followed by a spotting assay, finally yielding 13 TAM-sensitive genes under the drug-induced haploinsufficient condition. For these 13 TAM-sensitive genes, we conducted a comparative analysis of their Gene Ontology (GO) 'biological process' terms identified from other genome-wide screenings of the budding yeast deletion library and the MCF7 breast cancer cell line. Several TAM-sensitive genes overlapped between the yeast strains and MCF7 in GO terms including 'cell cycle' (cdc2, rik1, pas1, and leo1), 'signaling' (sck2, oga1, and cki3), and 'vesicle-mediated transport' (SPCC126.08c, vps54, sec72, and tvp15), suggesting their roles in the ER-independent cytotoxic effects of TAM. We recently reported that the cki3 gene with the 'signaling' GO term was related to the ER-independent antifungal action mechanisms of TAM in yeast. In this study, we report that haploinsufficiency of the essential vps54 gene, which encodes the GARP complex subunit, significantly aggravated TAM sensitivity and led to an enlarged vesicle structure in comparison with the SP286 control strain. These results strongly suggest that the vesicle-mediated transport process might be another action mechanism of the ER-independent antifungal or cytotoxic effects of TAM.

• Animal Bioscience
• /
• v.36 no.2
• /
• pp.175-190
• /
• 2023

Objective: The study was conducted to screen differentially expressed long noncoding RNA (lncRNA) in chickens by high-throughput sequencing and explore its mechanism of action on intramuscular fat deposition. Methods: Herein, Rose crown and Cbb broiler chicken embryo breast and leg muscle lncRNA and mRNA expression profiles were constructed by RNA sequencing. A total of 96 and 42 differentially expressed lncRNAs were obtained in Rose crown vs Cobb broiler chicken breast and leg muscle, respectively. lncRNA-ENSGALT00000046546, with high interspecific variability and a potential regulatory role in lipid metabolism, and its predicted downstream target gene 1-acylglycerol-3-phosphate-O-acyltransferase 2 (AGPAT2), were selected for further study on the preadipocytes. Results: lncRNA-46546 overexpression in chicken preadipocyte 2 cells significantly increased (p<0.01) the expression levels of AGPAT2 and its downstream genes diacylglycerol acyltransferase 1 and diacylglycerol acyltransferase 2 and those of the fat metabolism-related genes peroxisome proliferator-activated receptor γ, CCAAT/enhancer binding protein α, fatty acid synthase, sterol regulatory element-binding transcription factor 1, and fatty acid binding protein 4. The lipid droplet concentration was higher in the overexpression group than in the control cells, and the triglyceride content in cells and medium was also significantly increased (p<0.01). Conclusion: This study preliminarily concludes that lncRNA-46546 may promote intramuscular fat deposition in chickens, laying a foundation for the study of lncRNAs in chicken early embryonic development and fat deposition.