Ali Berkan Ural
Kafkas University, Turkey
Title: Computer aided analysis of breast based diagnostıc problems from mammograms using ımage processıng and deep learnıng methods
Biography
Biography: Ali Berkan Ural
Abstract
This paper presents analysis, evaluation and pre-diagnosis of early stage breast based diagnostic problems (breast cancer, nodules or lumps) by Computer Aided Diagnosing (CAD) system from mammogram radiological images. According to the statistics, the time factor is crucial to discover the disease in the patient (especially in women) as possible as early and fast. In this study, a new algorithm is developed using advanced image processing and deep learning methods to detect and classify the problem at early stage with more accuracy. This system first works with image processing methods (Image acquisition, Noise removal, Region Growing Segmentation, Morphological Operations, Breast Border Extraction, Advanced Segmentation, Obtaining Region Of Interests (ROIs) etc.) and segments the area of interest of breast and then analyzes the separately obtained area for cancer detection/lumps in order to diagnosis the disease. After segmentation, with using the Spectrogram images, 5 different deep learning based methods (specified Convolutional Neural Network (CNN) based AlexNet, ResNet50, VGG16, DenseNet, Xception) are applied to classify the breast based problems.