MEDICAL IMAGING FOR EARLY CANCER DIAGNOSIS AND EPIDEMIOLOGY USING ARTIFICIAL INTELLIGENCE: STRENGTHING NATIONAL HEALTHCARE FRAMEWORKS IN THE USA

Abstract

Cancer diagnosis and epidemiology have been significantly advanced through imaging-based methodologies, enabling early detection, precise tumor characterization, and effective treatment monitoring. This study systematically reviews 105 peer-reviewed case studies, focusing on the role of computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and mammography in improving cancer care infrastructure. The findings confirm that imaging-based screening programs, particularly low-dose CT for lung cancer and mammography for breast cancer, have led to substantial reductions in cancer mortality rates by facilitating early-stage diagnoses and timely interventions. The study also explores the growing role of imaging biomarkers and radiomics in tumor characterization, revealing that these advanced techniques enhance predictive accuracy in assessing tumor heterogeneity and treatment response. However, significant challenges persist, including geographic and socioeconomic disparities in imaging access, high costs associated with advanced imaging modalities, and the lack of standardization in radiomic feature extraction and validation. Moreover, the study identifies limitations in imaging-based prognosis models, with many lacking multicenter validation, thereby restricting their widespread clinical application. The review emphasizes the necessity for policy-driven solutions to bridge disparities in imaging accessibility, the development of standardized imaging protocols, and the integration of imaging biomarkers with molecular and genetic data to enhance precision oncology. Addressing these challenges through collaborative research and technological advancements will be crucial for optimizing the role of imaging in cancer detection, treatment planning, and patient outcome prediction.