Analysis of Breast Cancer Recognition in Histopathological Images using Convolutional Neural Network

The majority of women around the world will be diagnosed with breast cancer in their lifetime, making it the second leading cause of mortality among females. On the other hand, it is feasible to be cured of cancer if it is diagnosed at an early stage and given the appropriate treatment. By enabling patients to obtain timely therapeutic treatment, early breast cancer identification has the potential to significantly enhance both the prognosis and the odds of survival for those who are diagnosed with the disease. In addition, accurate categorization of benign tumors might assist patients in avoiding therapy that is not required. The advent of personalized medicine has resulted in a significant rise in the amount of work that must be done by pathologists as well as an increase in the complexity of digital pathology in cancer detection. Diagnostic protocols must now place equal emphasis on both efficiency and accuracy. Histopathology evaluations have been found to benefit from improvements in efficiency, accuracy, and consistency brought about by the application of computerized image processing technologies, which can also give decision support to assure diagnostic consistency. We demonstrate that convolutional neural networks, often known as CNN, can be an efficient method for identifying breast cancer histopathology images, and we test CNN's effectiveness as a binary predictor in the field of breast cancer diagnosis by using whole slide imaging. The model is trained using the data that can be found in the Kaggle archive. The suggested method is contrasted with other approaches already in use by employing a wide variety of achievement evaluation indicators.