An Efficient Way of Design of Framework using CNN and MLP Algorithms to find B Cancer

Cancer is a formidable worldwide health concern, characterised by a notable death rate. Breast cancer is one of the main causes of this statistic, taking many lives annually. Prognostic progress has become more and more dependent on gene expression analysis, thanks to recent developments in deep learning algorithms and high-throughput sequencing technologies. Accompanying conventional diagnostic-imaging indicators such as breast density and tissue texture, which are extensively employed by medical professionals and automated technologies, accurate determination of cancer risk is extremely valuable in directing tailored screening and prophylactic measures. Deep learning has become a potent tool for classification and prediction problems in this setting, especially in the field of breast imaging. Here, we present a brand-new deep learning method intended to estimate the risk of breast cancer. Using the CNN and MLP architecture, our approach expands on transfer learning Specifically, our model incorporates risk indicators to improve the evaluation of breast cancer risk, exhibiting better results than current approaches. This paper also examines risk markers for breast cancer, explaining how to utilise them appropriately and outlining their advantages and disadvantages when used with different risk prediction models. It also explores the growing significance of deep learning in risk assessment, highlighting the ability of our suggested model to automate several medical imaging modalities.