A HYBRID DEEP LEARNING APPROACH FOR BREAST CANCER DETECTION USING CNN AND RNN

Abstract

Breast cancer remains one of the most prevalent cancers among women worldwide, making early detection essential for effective treatment. This paper presents a novel approach to breast cancer detection using a hybrid architecture that combines Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). By harnessing the strengths of CNNs for feature extraction and RNNs for sequence analysis, this hybrid model aims to enhance the accuracy and efficiency of breast cancer detection from medical imaging data. In our approach, the CNN component extracts meaningful features from mammogram images, widely used in breast cancer screening. These features are then processed by the RNN, which captures temporal dependencies and patterns in the data. This combination enables the model to leverage both spatial and temporal information, providing more accurate and reliable breast cancer detection. The key contributions of this work include the development of a CNN-RNN hybrid architecture specifically tailored for breast cancer detection and its comprehensive evaluation on an extensive mammogram dataset. Results show that our hybrid model outperforms traditional CNN and RNN models in both accuracy and efficiency, underscoring its potential for improving breast cancer detection in clinical applications.