Mammograms Classification Using Gray-level Co-occurrence Matrix and Radial Basis Function Neural Network

Abstract

Computer Aided Diagnosis (CAD) is used to assist radiologist in classifying various type of breast cancers. It already proved its success not only in reducing human error in reading the mammograms but also shows better and reliable classification into benign and malignant abnormalities. This paper will report and attempt on using Radial Basis Function Neural Network (RBFNN) for mammograms classification based on Gray-level Co-occurrence Matrix (GLCM) texture based features. In this study, normal and abnormal breast image used as the standard input are taken from Mammographic Image Analysis Society (MIAS) digital mammogram database. The computational experiments show that RBFNN is better than Back-propagation Neural Network (BPNN) in performing breast cancer classification. For normal and abnormal classification, the result shows that RBFNN's accuracy is 93.98%, which is 14% higher than BPNN, while the accuracy of benign and malignant classification is 94.29% which is 2% higher than BPNN.

Content-Based Image Retrieval Techniques for Mammographic Images Using Soft Computing Techniques

“…A system to obtain salient regions with improved Region of Interest using graph based visual saliency methods was developed in [53] and performance was measured by Receiver Operating Characteristic curve. A Radial Basis Function neural network for mammogram classification based on Grey level Cooccurrence matrix was developed in [54]. An alternative method of mammogram classification was designed using Law's Texture Energy measure as texture feature extraction [55].…”

A Research on Mammograms Classification using Wavelets

“…Screening strategies like X-ray, MRI, and Ultrasound diagnosis give a huge amount of information that the surgeons or other specialists has to examine and to estimate about the diseasein a very less time [1]. Advanced technology pictures are used in CAD to highlight the observable segments where the disease is present; this helps the doctors to take a suitable decision by which they can cure the disease.…”

“…Characteristic masses or micro-classification are the processes which help to analyze the bosom cancer in its early stage [1].…”

“…Early identification of breast cancer is very important for proper treatment of the tumor which is due to bad contrast and less visibility in the mammographic pictures. Enhanced algorithms of computer-aided diagnosis help the specialists to accurately detect the disease [1].…”

“…Pratiwi, Alexander, J. Harefa, and S. Nanda [1]: uses the radial basis function neural network for characterization of mammograms in context of texture based elements. These texture based elements are extracted using gray level cooccurance matrix (GLCM).…”