Search

Breast cancer patients are more likely to have serious health problems and have a higher mortality rate. The primary reason could be radiologists misinterpreting dangerous lesions as a result of technological challenges with imaging quality and varying breast densities. Breast cancer early identification may increase survival rates. Mammography is a reliable method for spotting breast cancer in its early stages. A few of the image processing techniques required for the detection of breast cancer include preprocessing, segmentation, feature extraction, and classification. Segmentation is crucial in the tumor's identification process, meanwhile. This review focuses in particular on several problems with traditional and typical methodologies that make use of machine learning and deep learning techniques. Using conventional machine learning methods for manual breast cancer screening misunderstood the erratic feature-extraction process, requiring patients to return for biopsies to rule out any concerns. Although a number of deep learning-based methods for precise breast cancer categorization and prognosis have been established, few have offered a thorough analysis of lesions segmentation. We have proposed a domain specific Deep Learning based Modified U-net model at the end of this paper. In order to offer a thorough analysis of current diagnostic approaches, this study also looks into a variety of well-known databases using the phrase "Breast Cancer." [ABSTRACT FROM AUTHOR]