Abstract
Mass Detection and Classification System for Mammography Image Preprocessing
Highlights
The term “breast cancer” refers to a malignant tumor that has developed from cells in the breast
A method for detection and segmentation of masses using multiple thresholding, wavelet transform and genetic algorithm is employed in mammograms which were randomly selected from the Digital Database for Screening Mammography (DDSM).Jen C. et al proposed a high-performance CAD system for detecting abnormal mammograms by using the two-stage classifier ADC, which applied the PCA-based technique accompanied by robust feature weight adjustments
The k-nearest neighbor algorithm (k-NN) is a method for classifying objects based on closest training examples in the feature space. k-NN is a type of instance-based learning, or lazy learning where the function is only approximated locally and all computation is deferred until classification
Summary
The term “breast cancer” refers to a malignant tumor that has developed from cells in the breast. Breast cancer is a leading cause of death among women in developed countries. The morbidity of breast cancer is increasing with a fast speed in developing countries due to the increase of life expectancy, urbanization and change in life styles. As the cause of breast cancer is not clearly known, early detection remains the corner stone in breast cancer treatment. Breast cancer can be detected through various examinationas magnetic resonance imaging (MRI), mammography, ultrasound, CSE and BSE. In order to avoid unnecessary biopsies, the number of false positives in mammography has to be reduced.Before feature extraction and classification, the input mammogram image is pre-processed as shown in figure 1 in our method 3 steps are carried out in pre-processing. In second step input image is resized to standard size using resize function. Input mammogram image filtered to remove unwanted noise. Mammograms are medical images that are difficult to interpret, a preprocessing phase is needed in order to improve the image quality and make the segmentation results more accurate
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have