A novel neural-genetic algorithm to find the most significant combination of features in digital mammograms

Breast Cancer Detection using Image Processing Techniques

Breast Cancer is one of the significant reasons for death among ladies. Many research has been done on the diagnosis and detection of breast cancer using various image processing and classification techniques. Nonetheless, the disease remains as one of the deadliest disease. Having conceive one out of six women in her lifetime. Since the cause of breast cancer stays obscure, prevention becomes impossible. Thus, early detection of tumour in breast is the only way to cure breast cancer. Using CAD (Computer Aided Diagnosis) on mammographic image is the most efficient and easiest way to diagnosis for breast cancer. Accurate discovery can effectively reduce the mortality rate brought about by using mamma cancer. Masses and microcalcifications clusters are an important early symptoms of possible breast cancers. They can help predict breast cancer at it’s infant state. The image for this work is being used from the DDSM Database (Digital Database for Screening Mammography) which contains approximately 3000 cases and is being used worldwide for cancer research. This paper quantitatively depicts the analysis methods used for texture features for detection of cancer. These texture featuresare extracted from the ROI of the mammogram to characterize the microcalcifications into harmless, ordinary or threatening. These features are further decreased using Principle Component Analysis(PCA) for better identification of Masses. These features are further compared and passed through Back Propagation algorithm (Neural Network) for better understanding of the cancer pattern in the mammography image.

Ensemble Supervised Classification Method Using the Regions of Interest and Grey Level Co-Occurrence Matrices Features for Mammograms Data

Background:

Breast cancer is one of the most encountered cancers in women. Detection and classification of the cancer into malignant or benign is one of the challenging fields of the pathology.

Objectives:

Our aim was to classify the mammogram data into normal and abnormal by ensemble classification method.

Patients and Methods:

In this method, we first extract texture features from cancerous and normal breasts, using the Gray-Level Co-occurrence Matrices (GLCM) method. To obtain better results, we select a region of breast with high probability of cancer occurrence before feature extraction. After features extraction, we use the maximum difference method to select the features that have predominant difference between normal and abnormal data sets. Six selected features served as the classifying tool for classification purpose by the proposed ensemble supervised algorithm. For classification, the data were first classified by three supervised classifiers, and then by simple voting policy, we finalized the classification process.

Results:

After classification with the ensemble supervised algorithm, the performance of the proposed method was evaluated by perfect test method, which gave the sensitivity and specificity of 96.66% and 97.50%, respectively.

Conclusions:

In this study, we proposed a new computer aided diagnostic tool for the detection and classification of breast cancer. The obtained results showed that the proposed method is more reliable in diagnostic to assist the radiologists in the detection of abnormal data and to improve the diagnostic accuracy.

A STUDY ON GENETIC ALGORITHM BASED HYBRID SOFTCOMPUTING MODEL FOR BENIGNANCY/MALIGNANCY DETECTION OF MASSES USING DIGITAL MAMMOGRAM

In present works authors have developed a computerized classification procedure for tumor mass in breasts using digital mammogram. The process implements genetic algorithm and hybrid neuro-fuzzy approaches to classify tumor masses into benign and malignant group in order to assist the physicians for treatment planning. The classification process is based on accurate analysis of shape and margin of tumor mass appearing in breast. The shape features using Fourier descriptors introduce a large number of feature vectors. Thus, to classify different boundaries, a standard multilayer preceptor needs large number of inputs. Simultaneously, to train the network, a large number of training cycles and huge memory are also required. It is obvious that a complicated structure invites the problem of over learning and misclassification. In proposed methodology genetic algorithm (GA) has been used for the searching of effective input feature vectors. Adaptive neuro-fuzzy model has been used for final classification of different boundaries of tumor masses. The proposed technique is an innovative soft computing approach that removes the limitation of conventional neural networks and indicates a promising direction of adaptation in a changing environment. The classification system utilizes a Euclidean distance function to detect the belongingness of masses in benign and in malignant classes along with degree of benignancy/malignancy. Presently 200 digitized mammograms from MIAS and other databases have been considered for the experiment and which have shown an average of approximately 86% correct classification as compared with clinical data with a highest rate of 88.9%.