Neural Network is utilized as a developing analytic tool for the diagnosis of breast cancer. The goal of this research is to determine breast tumor from digital mammograms with a machine learning technique in view of RF and combination of RF-ELM classifier. For digital mammogram images, MIAS database is used. Preprocessing is usually needed to enhance the low quality of the image. The region of interest (ROI) is determined in line with the scale of suspicious region. After the suspicious area is sectioned, features are extracted by texture analysis. GLCM is used as a texture attribute to extract the suspicious area. From all extracted features best features are selected with the help of CBF method. To enhance the exactness of classification, only six features are selected. These features are mean, standard deviation, kurtosis, variance, entropy and correlation coefficient. RF and RF-ELM are used as a classifier. The outcomes of present work show that the CAD system with the usage of RF-ELM classifier may be very powerful and achieves the exceptional results in the prognosis of breast cancer.

Detection and classification of breast cancer from digital mammograms using RF and RF-ELM algorithm

Since last 60 years, bosom (breast) tumor is the major cause of death amid females worldwide. Earliest possible detection will raise the endurance rate of patients. Premature detection of bosom tumor is big challenge in medical science. Medical studies proven that imaging modalities like mammography, thermography, ultrasound, and magnetic resonance imaging (MRI) play a vigorous role to detect breast irregularity earliest. This paper enhances the knowledge on two imaging practices, one is mammography and another is thermography. It aids to identify the limitations in existing technologies and helps to plan the new methodology.

Role of Imaging Modality in Premature Detection of Bosom Irregularity

Breast cancer is the most prevailing type of cancer responsible for a large number of deaths every year. However, at the same time, this is largely a curable type of cancer if identified at initial stages. With major advances in research in the areas of image processing, data mining and clustering and machine learning, a more precise prognosis and prediction of breast cancer are possible at earlier stages. A fuzzy clustering model is a popular model used across various researches in image processing to predict the malignancy of breast tumor. The partitional clustering method finds its strength in its fuzzy partitioning such that a data point may belong to different classes with varying degrees of membership (ranging between 0 and 1), which is less rigid as compared to an older and still popular k-means clustering algorithm. The current article attempts to hybridize the fuzzy C-means with the cohort intelligence (CI) algorithm to optimize cluster formation. CI is a robust optimization metaheuristic belonging to the class of socio-inspired optimizers (Kumar M, Kulkarni A Socio-cultural inspired metaheuristics, pp 1–28, Springer International Publishing, 2019 [22]), motivated from self-adapting behavior of candidates in a cohort or a group. CI is typically characterized by its simple algorithmic nature, robust structure and a faster convergence rate, hence gaining popularity. This novel hybridized data clustering algorithm fuzzy-CI imitates the soft clustering and communal learning attitude of clusters and candidates. The hybridized method of fuzzy-CI is validated by testing it on the Breast Cancer Wisconsin (Diagnostic) Dataset. The results validate that the hybridized version exhibits better cluster formation in comparison with the non-hybridized version.

A Hybridized Data Clustering for Breast Cancer Prognosis and Risk Exposure Using Fuzzy C-means and Cohort Intelligence

The breast cancer is diagnosed using many ways for past two decades. The Studies have proved that the early detection of cancer will increase the life span of the patients. The breast cancer detection requires double reading of mammogram by radiologist, hence the radiologist need to have support from CAD which includes different image processing techniques. We are in urge to improve the CAD systems that detects the abnormalities such as micro calcification, mass, etc. than existing. Firstly, This paper focus on the preprocessing which removes noise from the mammogram and it is followed by segmentation of the image which helps to partition the image and to identify the abnormalities which could cause cancer. The segmentation is made by OTSU's method which helps us further to classify the abnormalities from the normal.

Kansagra Deep Mukeshbhai

Papers

Identification of abnormility from digital mammogram to detect breast cancer