Sahu, Ram Shankar (2015) Analysis of Mammographic Images for Early Detection of Breast Cancer Using Machine Learning Techniques. MTech thesis.
Breast cancer is the main reason for death among women. Radiographic images obtained from mammography equipment are one of the most frequently used techniques for helping in early detection of breast cancer. The motivation behind this study is to focus the tumour types of breast cancer images .It is methodology to anticipated a sickness in view of the visual conclusion of breast disease tumour types with precision, particularly when numerous feature are related. Breast Cancer (BC) is one such sample where the phenomenon is very complex furthermore numerous feature of tumour types are included. In the present investigation, various pattern recognition techniques were used for the classification of breast cancer using mammograms image processing techniques .The pattern recognition techniques for tumour image enhancements, segmentation, texture based image feature extraction and subsequent classification of breast cancer mammogram image was successfully performed. When two machine learning techniques such as Artificial Neural Network (ANN), Support Vector Machine (SVM) were used to classify 120 images, it was observed from the results that Artificial Neural Network classifiers demonstrated the h classification rate 91.31% and the SVM with both Radial Basis Function (RBF) and linear kernel classifiers demonstrated the highest classification rate of 92.11% and RBF classification rate is 92.85%.
|Item Type:||Thesis (MTech)|
|Uncontrolled Keywords:||Breast Cancer, Mammographic Images, Image Enhancement, Image Segmentation, Feature Extraction, Principal Component Analysis, ANN, SVM|
|Subjects:||Engineering and Technology > Biomedical Engineering|
|Divisions:||Engineering and Technology > Department of Biotechnology and Medical Engineering|
|Deposited By:||Mr. Sanat Kumar Behera|
|Deposited On:||18 Sep 2016 14:14|
|Last Modified:||18 Sep 2016 14:14|
Repository Staff Only: item control page