AI-Driven Breast and Lung Cancer Detection

Computer Engineering

Cancer, notably breast and lung cancer, continues to pose a global health threat, emphasizing the need for early detection strategies to improve survival rates. This literature survey focuses on AI-driven early detection of breast and lung cancer through deep learning and Convolutional Neural Network (CNN) models. A novel automated system for breast cancer detection is proposed, employing techniques like convolutional neural networks, sparse autoencoder, and stacked sparse autoencoder. Comparative analyses underscore the superiority of the stacked sparse autoencoder, presenting a robust and accurate non-invasive detection solution. Shifting to lung cancer, early diagnosis is crucial, prompting a critical assessment of existing computer-aided diagnosis techniques. A new model for lung cancer detection is proposed to enhance accuracy. With lung cancer being a leading global cause of mortality, the review explores advanced technologies in computed tomography (CT) screening. The analysis aids radiologists in precise assessments, addressing challenges posed by vast CT image information.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.