Artificial intelligence in translational immunology: bridging medical imaging, biologic drug discovery, and precision monitoring

The rapid integration of artificial intelligence (AI) into immunology is reshaping the discipline from descriptive to predictive science. Immune-mediated diseases—such as systemic lupus erythematosus (SLE), multiple sclerosis (MS), transplant rejection, and immune-related adverse events (irAEs)—exhibit remarkable heterogeneity at molecular, cellular, and tissue levels. Medical imaging across radiology, ophthalmology, digital pathology, and dermatology provides a non-invasive view of these complex phenotypes, while biologic therapies offer targeted and effective interventions. However, there remains a critical gap between imaging-derived representations of immune activity and computational systems capable of linking these data to mechanistic insights, therapeutic responses, and longitudinal disease trajectories. Building on recent advances in deep learning, foundation models, and multimodal fusion, this Research Topic seeks to consolidate emerging AI-driven approaches that bridge fundamental immunology with clinical and translational applications.This Research Topic aims to unify scattered efforts across imaging and computational domains into a coherent framework of AI-powered translational immunology. The first objective is to transform fragmented imaging applications into a structured discipline of AI immuno-imaging, enabling cross-disease insight and shared data standards. While AI has achieved major milestones in general pathology and radiology, its immune-specific use cases—such as lupus nephritis scoring, uveitis prediction, or digital quantification of inflammatory dermatoses—remain isolated. The second objective is to establish the missing link between imaging-based endophenotypes and therapeutic decision-making. We encourage contributions exploring whether multimodal AI models can predict individual response to biologic therapy, forecast drug immunogenicity, or reveal mechanistic correlates of immune activation. By connecting imaging biomarkers with drug-intelligent analytics, this Research Topic envisions a new roadmap for data-driven, precision-guided immunology.We welcome Original Research, Reviews, and Perspectives advancing the integration of AI with systems-level immunologic understanding. To generate new insights at the intersection of data science and translational research, contributions may include but are not limited to the following themes:• AI-driven immuno-phenotyping via medical imaging: deep learning for MRI/CT in neuroinflammation; fundus imaging for uveitis; digital pathology for renal immune diseases, tumor immune microenvironment (TIME), and transplant rejection.• AI in dermatology and surface imaging: automated scoring of inflammatory dermatoses (psoriasis, atopic dermatitis); detection of immune-related adverse events (irAEs) from checkpoint inhibitors.• AI-assisted biologic drug development: computational antibody design; prediction of immunogenicity and treatment response using large language models (LLMs) or graph neural networks.• Multimodal integration for precision therapeutics: fusion of imaging, single-cell, spatial, and clinical data to stratify patients in rheumatology, allergology, and transplantation.• Systems immunology and bioinformatics: analysis of immune repertoires (TCR/BCR sequencing) and modeling of dysregulated signaling networks. Topic editors: Chubin Ou, Wei Luo, Simon Fong Source: https://www.frontiersin.org/research-topics/81681/artificial-intelligence-in-translational-immunology-bridging-medical-imaging-biologic-drug-discovery-and-precision-monitoring