Breast cancer should be diagnosed as early as possible. A new approach of the diagnosis using deep learning for breast cancer and the particular process using segmentation strategies presented in this article. Medical imagery is an essential tool used for both diagnosis and treatment in many fields of medical applications. But, it takes specially trained medical specialists to read medical images and make diagnoses or treatment decisions. New practices of interpreting medical images are labour exhaustive, time-wasting, expensive, and prone to error. Using a computer-aided program which can render diagnosis and treatment decisions automatically would be more beneficial. A new computer-based detection method for the classification between compassionate and malignant mass tumours in mammography images of the breast proposed. (a) We planned to determine how to use the challenging definition, which produces severe examples that boost the segmentation of mammograms. (b) Employing well designing multi-instance learning through deep learning, we validated employing inadequately labelled data of breast cancer diagnosis using a mammogram. (c) The study is going through the Deep Lung method incorporating deep multi-dimensional automated identification and classification of the lung nodule. (d) By combining a probabilistic graphic model in deep learning, it authorizes how weakly labelled data can be used to improve the existing breast cancer identification method. This automated system involves manually defining the Region Of Interest (ROI), with the region and threshold values based on the next region. The High-Resolution Multi-View Deep Convolutional Neural Network (HRMP-DCNN) mainly developed for the extraction of function. The findings collected through the subsequent in available public databases like mammography screening information database and DDSM Curated Breast Imaging Subset. Ultimately, we'll show the VGG that's thousands of times quicker, and it is more reliable than earlier programmed anatomy segmentation. © 2020 - IOS Press and the authors. All rights reserved.