AI 与生物信息学协同用于脑疾病精准医学：整合影像组学与多组学数据
AI-bioinformatics synergy for precision medicine in brain diseases: integrating radiomics and multi-omics data
一篇综述系统梳理了 AI 与生物信息学整合框架如何将影像组学与基因组学、转录组学、蛋白质组学等多组学数据融合，以更全面建模脑疾病复杂性。文章指出，尽管两个领域各自都有进展，影像组学与多组学融合的联合应用仍未被充分利用。借助深度学习和图神经网络等表征学习方法，这类多模态系统可支持生物标志物发现、患者分层和个性化治疗策略。作者重点评估了数据异质性、可解释性有限和临床验证障碍等挑战，并以胶质瘤、阿尔茨海默病和多发性硬化症的案例说明统一影像-组学架构的临床价值。
来源：Briefings in Bioinformatics · doi.org
The convergence of artificial intelligence (AI) and bioinformatics is reshaping the landscape of precision medicine in brain diseases, particularly in neurological diseases and brain tumors. Despite advances in both fields, the combined application of radiomics and multi-omics fusion remains underutilized, even though integrative frameworks are essential for addressing the complexity and heterogeneity of imaging and molecular data. This review examines how integrative AI-bioinformatics frameworks enable the fusion of radiomics with genomics, transcriptomics, proteomics, and other omics modalities to more comprehensively model disease complexity. Leveraging deep learning, graph neural networks, and advanced representation learning, these multimodal systems facilitate biomarker discovery, patient stratification, and personalized treatment strategies. We critically evaluate key challenges including data heterogeneity, limited interpretability, and barriers to clinical validation, and highlight emerging solutions aimed at enhancing reproducibility and translational readiness. Case studies in gliomas, Alzheimer’s disease, and multiple sclerosis illustrate the clinical utility of unified imaging-omics architectures. Ultimately, this review positions radiomics and multi-omics integration as a foundational approach for the next generation of precision medicine in brain diseases by bridging the gap between computational innovation and clinical application.