AI-Enhanced Imaging Genomics: Linking Radiologic Patterns to Genotype in Sickle Cell Anemia – A Narrative Review

Abstract

Sickle cell anemia (SCA) is a genetically inherited hemoglobinopathy characterized by chronic hemolysis, vaso-occlusion, and multi-organ damage. While the underlying β-globin mutation is well-defined, the clinical course is highly heterogeneous, influenced by co-inherited genetic modifiers and environmental factors. Radiologic imaging plays a critical role in detecting both acute complications and chronic end-organ damage. Imaging genomics, an emerging field that correlates imaging features with genomic data, offers a novel pathway to understand the genotype–phenotype relationships in SCA. The integration of artificial intelligence (AI) into this domain has further enhanced the ability to identify subtle imaging biomarkers that may correspond to specific genetic profiles. AI-enhanced imaging genomics leverages machine learning algorithms to process high-dimensional imaging data, extract quantitative features, and integrate them with genomic information. In SCA, this approach can reveal patterns linked to disease severity, predict the risk of complications such as stroke or avascular necrosis, and monitor treatment response. Advanced imaging modalities—including MRI, ultrasound, and CT—combined with AI-driven analytics, can uncover microstructural and functional changes before they become clinically apparent. These predictive capabilities have the potential to refine diagnosis, improve risk stratification, and guide personalized therapeutic interventions