• K. Yaswanth Kumar
• P. Yasaswi
• M. Akhil Satya
• P. Mohan

Improved early detection techniques are required because breast cancer is still a problem for the world's health. This study employs medical pictures to investigate the potential of deep early breast cancer identification. In this study, deep learning, a branch of artificial intelligence, is crucial. For the automatic extraction of intricate patterns and characteristics from medical images, it provides a strong framework. Our initiative intends to recognize small anomalies and cell growth patterns suggestive of breast cancer at its early stages through the application of deep learning techniques, such as semantic segmentation, it involves using deep learning to precisely classify and delineate cancerous and non-cancerous regions within medical images, such as mammograms, aiding in early and accurate detection. This technology assists radiologists in identifying and assessing breast cancer lesions, improving diagnostic accuracy and patient outcomes. Our study aims to elucidate the complex tissue dynamics underlying breast cancer growth by examining a large collection of medical images. The improvement of early detection rates, which will help to improve patient outcomes and lower morbidity and mortality, offers significant potential for this ongoing effort. We believe that this technology will be crucial in advancing the field as we continue to develop our strategy and acquire more data, ultimately helping those who are at risk of breast cancer by providing more efficient and convenient screening options.

Semantic Segmentation, Transfer Learning, deep learning, U-net Model, Cnn.

"Leveraging Deep Learning For Early Breast Cancer Detection Through Semantic Segmentation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.i1-i7, March-2024, Available :http://www.jetir.org/papers/JETIR2403801.pdf

"Leveraging Deep Learning For Early Breast Cancer Detection Through Semantic Segmentation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppi1-i7, March-2024, Available at : http://www.jetir.org/papers/JETIR2403801.pdf