No abstract

Objective:The death rate of breast tumour is falling as there is progress in its research area. However, it is the most common disease among women. It is a great challenge in designing a machine learning model to evaluate the performance of the classification of breast tumour. Methods: Implementing an efficient classification methodology will support in resolving the complications in analyzing breast cancer. This proposed model employs two machine learning (ML) algorithms for the categorization of breast tumour; Decision Tree and K-Nearest Neighbour (KNN) algorithm is used for the breast tumour classification. Result: This classification includes the two levels of disease as benign or malignant. These two machine learning algorithms are verified using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset after feature selection using Principal Component Analysis (PCA). The comparison of these two ML algorithms is done using the standard performance metrics. Conclusion: The comparative analysis results indicate that the KNN classifier outperforms the result of the decision-tree classifier in the breast cancer classification.

No abstract

In this study, abnormalities in medical images are analysed using three classifiers, and the results are compared. Breast cancer remains a major public health problem among women worldwide. Recently, many algorithms have evolved for the investigation of breast cancer diagnosis through medical imaging. A computer‐aided microcalcification detection method is proposed to categorise the nature of breast cancer as either benign or malignant from input mammogram images. The standard mammogram image corpus, the Mammogram Image Analysis Society database is utilised, and feature extraction is performed using five different wavelet families at level 4 and level 6 decomposition. The work is accomplished through firefly algorithm (FA), extreme learning machine (ELM) and least‐square‐based non‐linear regression (LSNLR) classifiers. The performance of the classifiers is compared by benchmark metrics, such as total error rate, specificity, sensitivity, area under the receiver operating characteristic curve, precision, F1 score and the Matthews correlation coefficient. As validation of the classifier results, a kappa analysis is included to determine the agreement among classifiers. The LSNLR classifier attains a 3% to 7% improvement in average accuracy compared with the average classification accuracy of the FA (86.75%) and ELM (90.836%) classifiers.

No abstract

The survival rates of breast cancer are going up due to the emerging increase in its screening and diagnosis methods. However, breast cancer is yet the most intrusive disease found in women. Many techniques are emerging during recent years for the investigation of breast cancer using imaging modalities. The paper intends to categorize the severity present in the digital mammography images as either benign (B) or malignant (M) using an improved crow‐search optimization algorithm (ImCSOA). In the literature, the CSOA is generally used for solving several feature selection and numerical optimization problems. The objective is to utilize this popular optimization algorithm for the problem of biomedical image classification. However, if this algorithm is applied directly to classification problems, then it will result in poor classification of data. Hence, the original CSO (OCSO) algorithm undergoes suitable enhancements using a novel controlled parameter tuning, control operator and chaotic‐maps‐based controlled randomness. Four distinct chaotic maps are used for controlling the randomness in the OCSO algorithm. The mammogram images are obtained from the Mammographic Image Analysis Society and Digital Database for Screening Mammography data sets for the evaluation. The classification is accomplished through discrete wavelet transform‐based statistical features that are extracted at two levels [level 4 (L4) and level 6 (L6)] of decomposition. For both data sets, the ImCSOA with L4 and L6 decomposed bior4.4 wavelet features provides the maximum accuracy of around 85% to 86%, which is approximately 62% to 88% better than the OCSO algorithm with L4 and L6 decomposed bior4.4 wavelet features.

To improve the state-of-the-art works in breast cancer diagnosis, this paper proposes ensemble-based deep-transfer learning with classifiers namely optimizable K-nearest neighbors, optimizable naïve Bayes, optimizable ensemble, and optimizable support vector machine algorithms for the auto-feature extraction, detection, and severity classification of input mammograms. The hyperparameters of these classification algorithms are optimized by using the Bayesian optimization technique. The extracted robust features are normalized and then classified using the Bayesian optimized classifiers. Thus, the work throws a light of research on detecting whether the input mammogram is normal or abnormal. Afterward, it further focuses on the severity classification of abnormalities that is, benign or malignant. The aforesaid algorithms are trained and tested for the three-class classification problem, thus achieving a maximum performance using the Bayesian optimized SVM algorithm applied with ResNet18 deep features providing classification accuracy of 99.689% for MIAS and 98.883% for INbreast dataset.

No abstract