Breast cancer is a significant global health concern, requiring advancements in screening methods to better patient outcomes and early identification. This work explores the integration of deep learning techniques with Digital Breast Tomosynthesis (DBT) on 3D Digital Imaging and Communications in Medicine (DICOM) images to transform breast cancer screening. Our motivation stems from the potential synergy between deep learning’s pattern identification skills and DBT’s comprehensive breast tissue imaging. By using Deep Convolutional Neural Networks (DCNNs), YOLO v8 for Region-based Convolutional Neural Network (R-CNN), Faster R-CNN, and the Detectron2 framework for module identification, we automate the process of identifying benign and malignant lesions in breast images. By collaborating, we aim to reduce the amount of effort involved in manual interpretation, allowing medical staff members to focus on more challenging cases. The ultimate goal is to enhance patient outcomes by increasing diagnosis accuracy and reducing false positive rates in breast cancer screening. The results of our study indicate that deep learning in conjunction with DBT has a promising future, providing a more precise and effective means of breast cancer screening. This discovery has the potential to significantly change the field of breast cancer diagnostics, promoting earlier identification and improved patient treatment.