An Intelligent Method for Diagnosis of Breast Cancer

2017 International Journal of Innovative Research in Electronics and Communications  
INTRODUCTION Recently, the significance of image processing and machine vision is increasing in industrial automation, security, health, and traffic control in parallel with the developments in engineering technology. Breast cancer is one of the most common cancers among women, which is the second most common cause of death in women. Breast cancer is an uncontrolled growth of abnormal cells that occurs in different regions of the breast. [1] [2] [3] [4] As mentioned, the timely diagnosis of
more » ... st cancer dramatically reduces the mortality rate in the female population. Needle aspiration testing is a simple, inexpensive and non-invasive method for accurate and early diagnosis of this cancer, which today is attempted to be smart and machine-made. The steps to create an intelligent system for detecting breast cancer include: recording microscopic images from fine needle sampling, extracting numerical features from these images, selecting separation features, and designing and classifying tests. Most applied data sets, including the breast cancer data set, include a large number of examples and many features. Since this set of data may be aggregated for non-performing reasons (such as categorization), they may include many additional or unnecessary features. Therefore, in this situation, diminishing the dimensions of the inputs is necessary. Extracting valuable information from such a collection requires a complete search of the collection, which itself creates other challenges, such as complexity management and computational time. A common practice to overcome these problems is to use dimension reduction techniques such as feature selection.[3-7] Selecting a subset of features can increase class accuracy by reducing the predictive error by reducing the number of final samples. Breast cancer may occur in the tissues of the breasts like the dairy that carry the milk, in a tissue that produces non-germs. Breast cancer after skin cancer is the second most common cancer in women. According to the National Cancer Institute of the United States, one out of every eight women suffers from breast cancer. It can be easily treated if diagnosed on a timely basis. The risk of breast cancer increases with age. About three quarters of the cases of breast cancer develop in women over 50 years Abstract: Diagnosis of breast cancer dramatically reduces the mortality rate in the female population. mamography image processing is a computer aided method which enhances the amount of detail visible on a digitalized image. The effect of this technique in the diagnoses of breast cancer, where the detection of early malignant tumors is essential for effective treatment, is reviewed in this paper. The mammograms display a small percentage of the information they detect and that is due to the minor difference between normal glandular tissues and malignant disease. The digital medical image processing uses denoising and image enhancement techniques so as to reveal any tumors that may not be obvious and help the surgeons decide. The idea is to transform the data into the wavelet basis, in which the large coefficients are mainly the signal and the smaller ones represent the noise and using particle swarm optimization for high precision and feature detection. In this paper we employ evolutionary method of image enhancement, Particle swarm optimization algorithm and wavelet decomposition accompany with denoising are implemented and the conclusion would be satisfied.
doi:10.20431/2349-4050.0402002 fatcat:konhmjglone37ehz3dwagmf4fi