Loading...
Shashi Prabhat Ranjan is an Assistant Professor in the Department of CSE – Artificial Intelligence and Data Science at GMRIT Deemed to be University, Rajam, Andhra Pradesh. His academic role focuses on computer science, artificial intelligence, and data science.
Lung cancer is among the foremost contributors to cancer-related fatalities globally, necessitating prompt identification and precise categorisation to enhance patient prognoses. Medical imaging modalities such as computed tomography (CT), chest X-rays, and positron emission tomography (PET) are essential for detecting questionable lung abnormalities and aiding clinical diagnosis. Nonetheless, traditional image analysis can be labour-intensive and prone to discrepancies among different observers. Deep learning, especially convolutional neural networks (CNNs), transfer learning, and sophisticated attention-based frameworks, has surfaced as a favourable method for the automated identification and classification of lung cancer. This chapter elucidates the essentials of deep learning methodologies for lung cancer analysis, encompassing medical image capture and preprocessing, model architectures, detection and classification processes, evaluation metrics, explainable artificial intelligence, and concerns for clinical integration. It further addresses significant obstacles, such as restricted annotated datasets, class imbalance, domain variability, data leakage, model interpretability, privacy concerns, and legal mandates.