Breast Cancer Detection Using CNN and RNN

The treatment success for breast cancer depends heavily upon swift detection among females which represents one among the major cancer types affecting women globally. This paper fuses CNNs with RNNs into a combined model offering a new methodology for breast cancer diagnostic systems. Sensitivity of breast cancer diagnosis improves by combining CNN and RNN capabilities when analysing medical imaging data. The CNN component of the model extracts key features from mammography pictures, which are often used in breast cancer screenings. The RNN component then finds correlations and temporal patterns in the data after processing these attributes across time. This hybrid architecture improves the model's capacity to precisely and consistently identify breast cancer by combining temporal and spatial information. The two primary contributions of this work are the creation of a tailored hybrid CNN-RNN architecture for breast cancer detection and testing the system on a large repository of mammography images. Findings indicate that the hybrid model performs better in accuracy (99.9%) and efficiency as compared to standard CNN and RNN models and could be employed to improve clinical detection of breast cancer.