Accurate Detection and Diagnosis of Breast Cancer Using Scaled Conjugate Gradient Back Propagation Algorithm and Advanced Deep Learning Techniques

Development of breast cancer detection and its usage by different health care industries in their diagnostic center is a very much serious task for classifying cancer cells based on its specific characteristics. As a consequence, the classification process of the cancer becomes incredibly complicated for the potential users because they have a large set of attributes and parameters of the cancer cells which are available at their disposal in laboratory for diagnosis. Moreover, the proposed work gives the efficient decision for the classification of the cancer cells to diagnose the patients at there earlier stage of breast cancer. Design Methodology/approach: In this chapter, it has been proposed a layered neural network model which uses this back propagation algorithm along with scaled conjugate gradient for optimized way of classification of cancer cells by considering the appropriate parameters. Findings: The classification of cancer cells is evaluated using the proposed algorithm by designing a layered neural network model. For training the model, 70% of instances are used, for verification, 15% instances and for testing, 15% instances are used of 699 samples. After successful training of the model, the model classifies the cancers as benign (2) or malignant (4). Originality/value: The proposed methodology is an original scientific work and the algorithm used is an efficient algorithm for the classification of cancer cells. In this work, eleven data attributes are used for the classification from cancer data set.