Review of lung cancer detection

Lung cancer continues to be the leading cause of cancer-related deaths worldwide, with nearly 2 million new cases and 1.76 million deaths each year. Late diagnosis plays a major role in poor outcomes, making early detection critical to improving survival rates. Advances in computer science, especially in data mining, machine learning, and artificial intelligence (AI), present new opportunities to transform lung cancer research by enabling more accurate and timely diagnoses. This study reviews a range of computational models used in lung cancer detection and diagnosis, with particular emphasis on image analysis and predictive analytics. Methods such as convolutional neural networks (CNNs), attention mechanisms, and transformers have been utilized to improve the accuracy of lung nodule segmentation, classification, and malignancy prediction. This work investigates the application of AI-driven models for evaluating extensive datasets derived from CT scans, along with enhancements in diagnostic consistency and accuracy relative to human radiologists. The discussion addresses challenges of data integrity, model openness, and ethical considerations in integrating AI into therapeutic settings. This review provides an overview of the role of computer science in advancing lung cancer research, highlighting the possibilities for technological innovation. Interdisciplinary collaboration is essential for developing robust, intelligible, and scalable AI models that facilitate early diagnosis, enhance patient care, and seamlessly integrate into healthcare workflows. يعد التعاون متعدد التخصصات ضروريًا لتطوير نماذج AI القوية والواضحة والقابلة للتطوير التي تسهل التشخيص المبكر ، وتعزيز رعاية المرضى ، والاندماج بسلاسة في سير عمل الرعاية الصحية.