Digital Image Processing

J. Amjath Ali ¹, J. Janet ²

Affiliations
1 St.Peter’s University, Chennai, Tamil Nadu, IN
2 Dr.M.G.R.University (phase II), Chennai, Tamil Nadu, IN

Abstract

In this paper, Discrete Shearlet Transform (DST) basedmass classification system for digital mammogram is developed. Therecent enhancement in multi resolution analysis is DST whichdiminishes the disadvantage of the wavelets that they are not veryeffective if the images containing distributed discontinuities such as edges. Initially, the given mammogram is decomposed by using DSTwith various directions. The features used in depict the masses are theenergies of all directional sub-bands of the decomposed image. In theproposed method 2-level decomposition with 2 to 64 directions areused to extract the features. In the classification stage, Support VectorMachine (SVM) classifier with two levels is proposed. In the first onethe given unknown mammogram is classified into normal or abnormalcategory and finally the abnormal severity is classified into benign ormalignant. Experiments are conducted on Mammography ImageAnalysis society (MIAS) database. The average classificationaccuracy achieved for normal/abnormal is 88.72% andbenign/malignant is 94.74%.

Keywords

Shearlet Transform SVM Classifier, Digital Mammograms, Mass, Benign and Malignant.

Full Text

     

S. Meenalosini ¹, J. Janet ², E. Kannan ³

Affiliations
1 Veltech Dr.RR. & Dr.SR Technical University, Chennai, IN
2 Dean of Computing, Veltech Dr.RR. & Dr.SR Technical University, Chennai, IN
3 Dean & Professor, Veltech Dr.RR. & Dr.SR Technical University, Chennai, IN

Abstract

Breast cancer is one of the most dangerous diseases that cause innumerable fatal in the female society. Early detection is the only way to reduce the mortality. Due to variety of factors sometimes manual reading of mammogram results in misdiagnosis. So that the diagnosis rate varies from 65% to 85%. Various Computer Aided Detection techniques have been proposed for the past 20 years. Even then the detection rate is still not high. The proposed method consists of the following steps Preprocessing, Segmentation, Feature extraction and Classification. Noise, Artifact and Pectoral region are removed in preprocessing step. Contrast enhancement, alarm region generation and Region growing method is used to segment the mass region. Segmented features are extracted using Gray Level Co-occurrence Matrix. Extracted features are classified using Support Vector Machine. Performance of the proposed system is evaluated using partest method. Proposed algorithm shows 95.2% sensitivity and 94.4% Specificity. The proposed algorithm is fully automatic and will be helpful in assisting the radiologists to detect the malignancy efficiently.

Keywords

Mammogram, Computer Aided Detection, Adaptive Histogram, Segmentation, Feature Extraction, Support Vector Machine.

Full Text

     

S. Meenalosini ¹, J. Janet ¹

Affiliations
1 Veltech Dr. RR. & Dr. SR Technical University, Chennai, IN

Abstract

This paper presents a hybrid technique which aims to assist radiologist in identifying breast cancer at its earlier stages through mammograms. It is difficult to identify masses in raw mammogram. Hence, in this paper an intelligent system is designed to diagnose breast cancer in mammogram using intelligent techniques such as Gabor filter and gray level co-occurrence matrices. Preprocessing, Segmentation and mass extraction are the three major steps involved in the proposed method. In preprocessing, down sampling and quantization is applied on input mammogram, following it noise removal is efficiently performed using median filter and finally Region of Interest is extracted using histogram matching. In segmentation, a band-pass filter is formed by rotating a 1-D Gaussian filter(off center) in frequency space, termed as-Circular Gaussian Filter (CGF). A CGF can be uniquely characterized by specifying a central frequency and a frequency band. Usually mass appears as a brighter region on a mammogram. Mass region can be segmented out using a threshold that is adaptively decided upon the histogram analysis of the CGF-filtered mammogram. Finally extraction of masses is performed using gray level co-occurrence matrices (GLCM) features. GLCM Features like entropy, contrast and homogeneity is analyzed in order to detect whether extracted region contains masses or normal tissue. Efficiency of the proposed method is calculated by analyzing true positive, true negative and false positive, false negative results. Receiver Operating Characteristics curve method is used to analyze efficiency of the proposed method. Thus, the proposed approach would be helpful for automated real time breast cancer diagnosis.

Keywords

Gabour Filter, Gaussian Filter, Gray Level Co-Occurrence Matrices, Histogram Matching, Mammogram, Masses, Segmentation.

Full Text

     

Divya Mohandass ¹, J. Janet ²

Affiliations
1 St. Peter's University, IN
2 Veltech Dr. R.R. & Dr. S.R. Technical University, IN

Abstract

Medical images are very crucial in providing a good diagnosis. It becomes imperative for these medical images to be processed. In this paper, we present a lossless image coder based on wavelet transform. The efficiency of wavelet transform in representing smooth edges present in medical images has been proved in literature. It has good localization properties in spatial and frequency domain. Ostu's global thresholding algorithm and Huffman encoding are applied to the wavelet transformed image. This encoding algorithm has been applied to CT, MRI images. The drawback in wavelet when representing edges has been overcome by the contourlet transform. The proposed joint image compression algorithm was applied to the contourlet transformed image. Experimental results indicate a comparative approach of the proposed system between the wavelet and the contourlet transformed image. The results obtained were appreciable in terms of compression ratio and PSNR values.

Keywords

Lossless Compression, Global Thresholding, Huffman Encoding, Contourlet, Wavelet.

Full Text

     

S. Venkatalakshmi ¹, J. Janet ²

Affiliations
1 Department of CSE, Panimalar Institute of Technology, Chennai, IN
2 Sri Krishna College of Engineering and Technology, Coimbatore, IN

Abstract

Cancer is a life-threatening disease, which consumes numerous human lives. However, the lifespan of the patients can be extended, when the disease is treated properly at the right time. This article renders a small contribution to the medical world for detecting the abnormalities in the mammograms. The research goal is attained by four important phases such as mammogram pre-processing, segmentation, feature extraction and classification. In the pre-processing phase, median filter is utilized to enhance the quality of an image. The pre-processed image is then segmented by FCM. The features are extracted from the image by Gaussian Hermite Moments, which are proven to be simple, efficient and noise resistant. Finally, multiclass SVM classifies between the normal, malignant and benign kinds of cancer. The performance of the proposed approach is evaluated against several analogous approaches in terms of accuracy, sensitivity and specificity. The proposed approach shows convincing results.

Keywords

CAD System, Breast Cancer Detection, Mammogram Segmentation, Multi-Class SVM, Classification, Abnormality Detection, Gaussian Hermite Moments.

Full Text