Lung Cancer Detection Using Deep Learning

Lung cancer remains one of the most deadly diseases worldwide, with early detection being a crucial factor in improving survival rates. Traditional diagnostic methods often detect the disease at advanced stages, making early detection a challenge. This project focuses on the power of Long Short-Term Memory (LSTM) networks in combination with MobileNet, a lightweight Convolutional Neural Network (CNN), for more efficient and accurate lung cancer detection. MobileNet is used to extract relevant features from medical images such as CT scans and X-rays, benefiting from its efficiency and ability to work with fewer computational resources. The extracted features are then processed by the LSTM network, which is particularly effective in capturing sequential patterns and complex relationships within the data, helping to identify early-stage cancerous patterns that might not be immediately visible. This hybrid model combines the strengths of MobileNet in feature extraction with the ability of LSTMs to analyze sequential data, resulting in a more robust lung cancer detection system. The model’s ability to process images efficiently, while maintaining high accuracy, makes it suitable for real-time applications, particularly in mobile-based diagnostic systems and resource-limited environments. The proposed system demonstrated high performance in early stage cancer detection, offering the potential for widespread use in clinical practice and improving patient outcomes through faster diagnosis. This approach provides a promising step forward in the development of AI-driven tools for early lung cancer diagnosis.

Keywords: Long Short-Term Memory (LSTM), MobileNet, deep learning, feature extraction.