Deep learning models, particularly Convolutional Neural Networks and U-Net architectures, are successfully utilized for segmenting breast cancer histology images, enabling precise identification of anatomical structures and pathological lesions. This study highlights the effectiveness of the U-Net architecture in histology imaging and segmentation, demonstrating its potential to enhance the diagnosis process in medical imaging. Such advancements are crucial for improving the speed and accuracy of breast cancer diagnosis, potentially benefiting thousands of patients annually, primarily women, and advancing the development of deep learning models. Specifically, this model integrating ResNet+U-Net have been applied to early breast cancer detection, achieving an accuracy of 96.3%, a MeanIoU of 98.0%, and a specificity of 98.1%. These results underscore the significant impact of deep learning methods in diagnosing breast cancer, increasing patient life expectancy by facilitating early detection. Moreover, the study aims to refine the sensitivity and accuracy of these algorithms, thereby reducing false positives and negatives to render the treatment process more effective.