• Korean Journal of Artificial Intelligence
• /
• v.6 no.2
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7467-7472
• /
• 2015

Background: Breast cancer is known to be one of the most prevalent cancers among women in both developing and developed countries. The incidence of breast cancer in Pakistan has increased dramatically within the last few years and is the second country after Israel in Asia to have highest proportional cases of breast cancer. However, there are limited data for breast cancer available in the literature from Pakistan. Objectives: The study was conducted to bring to light the common clinical presentation of breast cancer and to evaluate the frequency of established risk factors in breast carcinoma patients and furthermore to compare the findings between premenopausal and postmenopausal women in Pakistan. Materials and Methods: A 6 months (from July 2012 to Dec 2012) cross sectional survey was conducted in Surgical and Oncology Units of Civil Hospital, Karachi. Data were collected though a well developed questionnaire from 105 female patients diagnosed with carcinoma of breast and analyzed using SPSS version 17. Institutional ethical approval was obtained prior to data collection. Results: Out of 105 patients, 43 were premenopausal and 62 were postmenopausal, 99 being married. Mean age at diagnosis was $47.8{\pm}12.4years$. A painless lump was the most frequent symptom, notived by 77.1%(n=81). Some 55.2% (n=58) patients had a lump in the right breast and 44.8%(n=47) in the left breast. In the majority of cases, the lump was present in upper outer quadrant 41.9% (n=44). Mean period of delay from appearance of symptoms to consulting a doctor was $5.13{\pm}4.8months$, from the shortest 1 month to the longest 36 months. Long delay (> 3 months) was the most frequent figure 41.9%. Considering overall risk factors most frequent were first pregnancy after 20 years of age (41%), physical breast trauma (28.6%), lack of breast feeding(21.9%), and early menarche <11 years (19%), followed by null parity (16.2%), consumption of high fat diet (15.2%), family history of breast cancer or any other cancer in first degree relatives (9.5% and 13.3%, respectively). Some of the less common factors were late menopause >54 years (8.6%), use of oral contraceptive pills (10.5%), use of hormone replacement therapy (4.7%),smoking (4.7%) and radiation (0.96%). Significant differences (p<0.005) were observed between pre and post menopausal women regarding history of physical breast trauma, practice of breast feeding and parity. Conclusions: A painless lump was the most frequent clinical presentation noted. Overall age at first child > 20 years, physical breast trauma, lack of breast feeding, early menarche <11 were the most frequent risk factors. Physical breast trauma, lower parity, a trend for less breast feeding had more significant associations with pre-menopausal than post-menopausal onset. Increase opportunity of disease prevention can be obtained through better understanding of clinical presentation and risk factors important in the etiology of breast cancer.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.706-709
• /
• 2006

Cancer is one of the major causes of death; however, the survival rate can be increased if discovered at an early stage for timely treatment. According to the statistics of the World Health Organization of 2002, breast cancer was the most prevalent cancer for all cancers occurring in women worldwide, and it account for 16.8% of entire cancers inflicting Korean women today. In order to classify the type of breast cancer whether it is benign or malignant, this study was conducted with the use of the discriminant analysis and the decision tree of data mining with the breast cancer data disclosed on the web. The discriminant analysis is a statistical method to seek certain discriminant criteria and discriminant function to separate the population groups on the basis of observation values obtained from two or more population groups, and use the values obtained to allow the existing observation value to the population group thereto. The decision tree analyzes the record of data collected in the part to show it with the pattern existing in between them, namely, the combination of attribute for the characteristics of each class and make the classification model tree. Through this type of analysis, it may obtain the systematic information on the factors that cause the breast cancer in advance and prevent the risk of recurrence after the surgery.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.4
• /
• pp.1193-1196
• /
• 2012

Breast and cervical cancer are the most common causes of cancer mortality among women worldwide, but they are largely preventable. There are limited data on knowledge and practices on screening methods of breast and cervical cancers among female health care workers in Sri Lanka, in spite of having an organized screening programme islandwide. A cross-sectional survey was conducted among 219 female health care workers including public health midwives (68.9%) selected from 6 districts in Sri Lanka using convenient sampling methods. A self-administered questionnaire was used as a pre-test in a capacity building training programme to collect the data. The mean (SD) duration of work experience of the respondents was 12 years and 52.5% were aged over 35 years. Most (76.7%) were married, and afamily history of cancer was reported by 24.2%. Over 98% knew about self breast examination. Even though 84.1% practiced it, only 47.9% practiced it on a monthly basis. Clinical breast examination and mammography were known by 94.1% and 64.3% respectively. Only 19.2% had undergone a clinical braest examination within one year and 3.6% had ever undergone a mamography. Only 76.3% knew that a Pap smear detects precancerous stage of cervical cancer. Among 169 married workers, 73.4% had never had a Pap smear and only 17.2% had got it done within the preceding 5 years. Among the reasons for not doing a pap smear within 5 years, 47.0% belived it as not nescessary, 17.3% due to fear/dislike, 23.2% as not having symptoms, 3% had not known about it and 3% not known about availability of services. The study findings suggest that the knowledge and practices on breast and cervical cancer screening methods among female health care workers need to be improved. Considering the role that health care workers play in communicating health behaviors to the general public, strengthening health education interventions for this group of females is essential.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.13
• /
• pp.5471-5476
• /
• 2015

2-deoxy-D-Glucose (2DG) causes cytotoxicity in cancer cells by disrupting thiol metabolism. It is an effective component in therapeutic strategies. It targets the metabolism of cancer cells with glycolysis inhibitory activity. On the other hand, MLN4924, a newly discovered investigational small molecule inhibitor of NAE (NEDD8 activating enzyme), inactivates SCF E3 ligase and causes accumulation of its substrates which triggers apoptosis. Combination of these components might provide a more efficient approach to treatment. In this research, 2DG and MLN4924 were co-applied to breast cancer cells (MCF-7 and SKBR-3) and cytotoxic and apoptotic activity were evaluated the by Micro culture tetrazolium test (MTT), TUNEL and ELISA methods. Caspase3 and Bcl2 genes expression were evaluated by real time Q-PCR methods. The results showed that MLN4924 and MLN4924/2DG dose-dependently suppressed the proliferation of MCF7 and SKBR-3 cells. Cell survival of breast cancer cells exposed to the combination of 2DG/MLN4924 was decreased significantly compared to controls (p<0.05), while 2DG and MLN4924 alone had less pronounced effects on the cells. The obtained results suggest that 2DG/MLN4924 is much more efficient in breast cancer cell lines with enhanced cytotoxicity via inducing a apoptosis cell signaling gene, caspase-3.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.8
• /
• pp.3353-3358
• /
• 2014

Breast cancer is the most common in women worldwide, with some 5-10% of all cases due to inherited mutations of BRCA1 and BRCA2 genes. Obesity, hormone therapy and use of alcohol are possible causes and over-expression of leptin in adipose tissue may also play a role. Normally surgery, radiation therapy and chemotherapy allow a good prognosis where screening measures are in place. New hope in treatment measures include adjuvant therapy, neoadjuvant therapy, and introduction of mono-clonal antibodies and enzyme inhibitors.

• Genomics & Informatics
• /
• v.19 no.2
• /
• pp.17.1-17.13
• /
• 2021

Breast cancer is one of the leading causes of cancer in women all over the world and accounts for ~25% of newly observed cancers in women. Epigenetic modifications influence differential expression of genes through non-coding RNA and play a crucial role in cancer regulation. In the present study, epigenetic regulation of gene expression by in-silico analysis of histone modifications using chromatin immunoprecipitation sequencing (ChIP-Seq) has been carried out. Histone modification data of H3K4me3 from one normal-like and four breast cancer cell lines were used to predict miRNA expression at the promoter level. Predicted miRNA promoters (based on ChIP-Seq) were used as a probe to identify gene targets. Five triple-negative breast cancer (TNBC)-specific miRNAs (miR153-1, miR4767, miR4487, miR6720, and miR-LET7I) were identified and corresponding 13 gene targets were predicted. Eight miRNA promoter peaks were predicted to be differentially expressed in at least three breast cancer cell lines (miR4512, miR6791, miR330, miR3180-3, miR6080, miR5787, miR6733, and miR3613). A total of 44 gene targets were identified based on the 3'-untranslated regions of downregulated mRNA genes that contain putative binding targets to these eight miRNAs. These include 17 and 15 genes in luminal-A type and TNBC respectively, that have been reported to be associated with breast cancer regulation. Of the remaining 12 genes, seven (A4GALT, C2ORF74, HRCT1, ZC4H2, ZNF512, ZNF655, and ZNF608) show similar relative expression profiles in large patient samples and other breast cancer cell lines thereby giving insight into predicted role of H3K4me3 mediated gene regulation via the miRNA-mRNA axis.

• Journal of the Korean Society of Radiology
• /
• v.84 no.2
• /
• pp.372-385
• /
• 2023

Breast cancer is one of the most common cancers and causes several complications in females. Currently, MRI is a necessary method for preoperative studies in patients with breast cancer. A high frequency of breast MRI can lead to an increase in the number of incidental extramammary findings. Moreover, it can provide accurate preoperative workup; therefore, the prognosis of patients can be improved. Herein, we provide several extramammary findings, including the mediastinum, lung, upper abdomen, bone, and soft tissue, correlating with US, chest CT, liver MRI, PET-CT, and bone scan.

• Journal of the Korean Society of Radiology
• /
• v.7 no.2
• /
• pp.151-156
• /
• 2013

As the number of cancer patients and its death rate increases, this study is to understand the occurrences in cancer patients in Busan area and to provide active help for treatment, prevention and management of cancer patients. It was investigated and analyzed based on 4462 patients who were diagnosed with cancer and received radiation therapy from Jan. 2011 to Dec. 2012 at tertiary medical institution in Busan area. The seven main cancer types were breast cancer, cervical cancer, lung cancer, colon rectal cancer, brain tumor, laryngopharyngeal cancer and liver cancer. The most common type of cancer was breast cancer which takes up 38.1% of cancer patients stood out from other cancer types. Breast cancer is that shows increasing trend and in need of appropriate countermeasures and managements for decreasing cancer risk. Therefore the causes and prevention of breast cancer analysis, an appropriate management program is required.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.15
• /
• pp.6347-6352
• /
• 2015

Background: Breast malignancies are one of the leading causes of deaths in females worldwide. There are a number of risk factors associated with breast cancer but in Karachi Pakistan there are insufficient data available. Materials and Methods: A case control study was conducted on females in age group between 30-80 years. This study was accomplished by retrospective data collection in Aga Khan University Hospital Karachi, Pakistan. A total of 108 females with primary malignancy of breast were included along with 108 matched controls. Relationship of various factors with disease was studied using logistic regression to calculate odds ratios with 95 % confidence intervals. Results: A total of 14 variables were analyzed and based on and 7 were found to be risk factors: old age, family history of breast cancer, family history of other carcinomas, personal history of breast carcinoma, early age of menarche, older age of mother at first delivery and lower number of children. Five factors, parity, breast feeding, history of oral contraceptive pills intake, past history of oophorectomy and hysterectomy showed protective associations. One variable, use of hormonal replacement therapy, showed a controversial link and one other, marital status, was not significant in this study. Conclusions: It is concluded that most of the well-known risk factors for breast cancer are also associated with the disease in the female population of Karachi, Pakistan. High risk patients should be the focus with the help of this study so that screening can be more effective for early diagnosis before clinically evident breast malignancy.