Breast cancer detection using Adaboost classifier
Abstract : Breast cancer is a deadly disease; an accurate and early diagnosis of breast cancer is the most efficient method to decrease the death rate.
But, in the early detection and diagnosis of breast cancer, differentiating abnormal tissues is a challenging task. In this paper, a weight-based AdaBoost algorithm is proposed for an effective detection and classification of the breast cancer.
An AdaBoost algorithm effectively classifies the breast cancer classes by adding the weights to the samples in the week classifier during the training phase.
A weighted vote is performed on the results of each week classifier, and the strong classifier is integrated according to the weight of the week classifier. The breast cancer image datasets named CBIS-DDSM and MIAS are utilized for effective classification. Tumor-like regions (TLRs) are diagnosed by utilizing the optimum method of Otsu thresholding to enhance training abilities. The convolutional neural network (CNN) architectures of the AlexNet and ResNet50 are utilized for the feature extraction.
A weight-based AdaBoost algorithm is proposed for the classification of breast cancer mammogram images into four classes benign calcification (BC), malignant calcification (MC), benign mass (BM) as well and malignant mass (MM).
The results shows that the proposed weight based AdaBoost algorithm delivers the performance metrics such as accuracy, specificity, sensitivity, precision and F1-score values about 99.56%, 99.38%, 99.40%, 98.89% and 99.18% respectively, which ensures the accurate classification results compared with the existing methods such as IMPAResNet50, Gray difference weight and MSER detector, MLO and CC methods.
The performance classification accuracy has been encouraging comparison with various existing classifiers implemented in the literature. As expected the proposed model classifies diagnosis cases into either cancerous or non cancerous with high amount of accuracy.
Even if technology has developed, still lots of people are facing many issues with modern age diseases. Breast cancer has become one of the most common deadliest diseases rising over days among all countries in world.
Ratio of this disease increases due to lack of awareness and late identification. Our result reveals ANN (machine learning) plays measure factor for detection of cancer diagnosis to save the human life from the dangerous disease.
Previous researches reveal the increasing threats of breast cancer which drive to delve into unsolved and problematic issue, which is the main reason for the work reported in this paper. In the early stage of the breast cancer it appear as a malevolent lump and later stage it growths uncontrolled and variable manner.
By the help of the feature selector the datasets is free from ambiguity and dimension of data is also reduced. It solves the over fitting problem of dataset
The no of stages varies within the problem description of BPNN (Back Propagation Neural Network) is a gradient descent algorithm used in various domains
The proposed weight based AdaBoost algorithm is utilized for breast cancer detection using CBISDDSM dataset. This section consists of four different stages which include data collection, extraction of TLRs, feature extraction and classification. Fig. 1 represents the workflow of the proposed breast cancer detection methodology
The experiments of this proposed method utilize the breast cancer dataset named digital database for screening mammography (DDSM) and mammographic image analysis society (MIAS). The curated breast imaging subset (CBIS-DDSM) [21] is a standard and advanced form of the DDSM dataset that is utilized to take not only normal cases but also abnormal cases
Some cases CAD (Computer Aided Tool) is also used by the physicians.
Various machine learning methods are used to detect whether the cancer gene is benign (or) malignant.
Then reduced data are used for ANN and classification has been performed
For classification radial basic function (RBF), General Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) were used.
|