فصلنامه بیماری های پستان ایران
سال نهم شماره 2 (پیاپی 33، تابستان 1395)

Breast Cancer is one of the common cancers in Iran. Each Prediagnosis of that can survive women from different risks. The aim of this research is classifying imbalanced dataset for detecting normal vs. abnormal women who came to ACECR Breast Cancer Clinic. Imbalanced datasets are one of the main challenges for designing medical decision support system. So, in this article, imbalanced data classification was addressed via data level solutions.
In this research for classifying of 918 women’ breast situation, the “AdaBoost.M1”, “K-nearest neighbor”, and “probabilistic neural network” as triple algorithms were used. Because of facing with imbalanced dataset, for solving that, “random over sampling”, “Random under sampling”, and “Synthetic Minority Over-sampling Technique” were used as 3 re-sampling methods. So, Mat lab and R as software tools were used for implementing of methods and algorithms. Also, the values of 60 features that extracted from women’s historical and physical exam forms were used as input data in triple algorithms. Finally, “precision” and “F-Measure” as two criteria were used for evaluating in test state of triple algorithms.
Based on “precision” and “F-Measure” as two useful criteria, the best performance of this research’s classification algorithms were through dataset that generated by Synthetic Minority Over-sampling Technique. So, the performance of “AdaBoost.M1”, “K-nearest neighbor”, and “probabilistic neural network” for classification of that dataset based on “precision” and “F-Measure” were “93.5,93.6”, “79.5,87.7”,and “86,91.9”respectively.
There are different methods for solving imbalanced datasets problem through classification of that. Re-Sampling is one of the popular data level methods. Through 3 re-sampling methods, the best classification algorithm performance belongs datasets that generated by “Synthetic Minority Over-sampling Technique”, So among triple algorithms and four datasets that were used in this research and the based on “precision” and “F-Measure”, AdaBoost.M1 had the best performance in classification.

Impulse noise removal of mammography image is of great importance. The presence of different signs and characteristics of the disease has made it difficult for physicians’ to diagnose. MLP neural network allows the analysis of the patients’ medical data for medical decisions. The goal of this paper is to present an accurate model designed for reduction of degradation caused by high density impulsive noise in mammography images.
In this study, the medical case files of 574 patients. Patient information was acquired from the Mortaz General Hospital Standard Database and selected. GBC Algorithm and MLP neural network are used for reduction of degradation Caused by high density impulsive noise in mammography images.
The suggested model was compared with the MDBUTMD and ATSM methods. In reduction of degradation caused by high density impulsive noise in mammography images, the suggested model acquired the least error and the most PSNR and validation in comparison with other methods. The ATSM method has the most error and least PSNR.
Subjective and objective evaluations on different images with different noise densities show the superiority of the proposed method over the related recent works in the field.

Mastectomy and movement limitations after breast cancer surgery, may cause changes in body posture by inducing disorders in body statistics and limitation of movements in spine, which alters Quality of Life. Defining these deformities may develop strategies to combat it. The aim of study is comparing Thoracic kyphosis and lumbar lordosis in breast cancer survivors compared to healthy women.
Study population consisted of 21 breast cancer survivors and 21 healthy age matched women referred to Seyed-khandan physiotherapy institute. A 60-cm-long flexicurve was used to measure the size of the curve in thoracic and lumbar spines and kyphosis and Lordosis angle were calculated. Mean difference of these angles and their correlated factors were studied.
Mean age of participants was 48.7 (±7.1) years old. There was no significant difference in demographic characteristics between two groups. Mean Lordosis in patients and healthy women were 50.74 and 48.38 respectively (p = 0.1) and mean degree of kyphosis were 55.28 and 40.59 in two groups. (P Breast cancer survivors experience more increased thoracic kyphosis compared to healthy women. Considering the correlation of increasing age and BMI with severity of this complication, Rehabilitation interventions for correction body posture and strengthening of muscles and suitable diet and physical activity for Gaining fitted BMI is suggested.

Today, cancer is the most common and important diseases worldwide which extensive research is done to prevent and treat cancer. HER3 is a membrane- bound protein that is encoded by ErBB3 gene. After heterodimerization with other family members it can be phosphorylated and activated. The aim of this study was HER3 expression investigation as a factor involve in the spread of breast cancer.
In this study 20 breast cancer and 20 healthy paraffin embedded tissue samples were collected from Mehr Hospital of Tehran in Jan up to Sep 1392. RNA was extracted from tissue samples by RNX solution, and then cDNA synthesis was carried out by Rnadom Hexamer and oligo dT primers and MMULV enzyme. After that PCR reactions were optimized for HER3 gene by using specific primers. PCR products were determined by electrophoresis in Agarose gel.
Her3 gene expression in 70% of patients samples due to the presence of bands observed on agarose gel and specific band were not observed in 30% of samples. In addition to, in 20% of normal samples PCR product were observed but in 80% of normal samples band didn’t observe.
on the base of results it could be said that ErbB3 expression is increased in breast cancer patients. Non- significant over expression in normal samples indicate that increased expression of HER3 is a reliable factor to detect the disease in early stages, or even thought it could be a prognostic factor in breast cancer.

Increased rumination and reduced resilience are psychological difficulties that are experienced by women with breast cancer. Therefore, the purpose of this research was to investigate the effectiveness of mindfulness training on enhancing resilience and reducing rumination in women patients with breast cancer.
The design of this randomized trial was pretest-posttest with the control group. The study sample included 40 women with breast cancer. Patients, who met entry requirements to design, randomly assigned into two intervention and control groups. Both groups completed rumination and resilience questionnaires. The intervention group received eight sessions of mindfulness training. After completing the course, posttest was conducted for both intervention and control groups.
Comparison of the two groups using t-test, showed that there are significant difference between the two groups in terms of resilience (t=5.22, P= 0/01) and rumination (t=-6.21, P= 0/01). In other words, mindfulness training was effective in increasing resilience and reducing rumination.
The findings suggest that mindfulness training can be considered as an effective intervention to increase resilience and reduce rumination in women with breast cancer. It is necessary to examine the efficacy of the intervention with other psychological variables.

Today, cancer is the most common and important diseases worldwide which extensive research is done to prevent and treat cancer. HER3 is a membrane- bound protein that is encoded by ErBB3 gene. After heterodimerization with other family members it can be phosphorylated and activated. The aim of this study was HER3 expression investigation as a factor involve in the spread of breast cancer.
In this study 20 breast cancer and 20 healthy paraffin embedded tissue samples were collected from Mehr Hospital of Tehran in Jan up to Sep 1392. RNA was extracted from tissue samples by RNX solution, and then cDNA synthesis was carried out by Rnadom Hexamer and oligo dT primers and MMULV enzyme. After that PCR reactions were optimized for HER3 gene by using specific primers. PCR products were determined by electrophoresis in Agarose gel.
Her3 gene expression in 70% of patients samples due to the presence of bands observed on agarose gel and specific band were not observed in 30% of samples. In addition to, in 20% of normal samples PCR product were observed but in 80% of normal samples band didn’t observe.
on the base of results it could be said that ErbB3 expression is increased in breast cancer patients. Non- significant over expression in normal samples indicate that increased expression of HER3 is a reliable factor to detect the disease in early stages, or even thought it could be a prognostic factor in breast cancer.