Imaging genomics is an emerging data science field that arises with the recent advances in acquiring multimodal imaging data and high throughput omics data. Its major task is to perform integrated analysis of imaging and omics data, often combined with other biomarker, clinical, and environmental data, to gain new insights into the underlying mechanism of human health and disease, which in turn will impact the development of new diagnostic, therapeutic and preventative approaches. Given the unprecedented scale, complexity and heterogeneity of the fast-growing big data in imaging geomics, we are facing major computational, statistical and analytical challenges that have to be met to realize the full potential of these valuable data.
The objective of this Research Topic is to foster new methodologies that could overcome the above challenges. We welcome submissions to propose new effective and efficient methods for analyzing big data in imaging genomics, and yield promising biomedical discoveries to better understand the biological pathways and mechanisms from genetic determinants, molecular and cellular signatures, tissue and organ level biomarkers, and to phenotypical outcomes. Topics include but are not limited to:
• Genetic or epistatic analysis of imaging phenotypes
• Genomic or multi-omics analysis of imaging phenotypes
• Predictive modeling via integrative imaging genomics
• Statistical methods and causal reasoning in imaging genomics
• Machine learning and deep learning in imaging genomics
• Collaborative or federated learning in imaging genomics
• Big data analytics in imaging genomics
• Biomarker discovery in imaging genomics
• Systems biology in imaging genomics
• Translational imaging genomics
• Precision medicine in imaging genomics
• Clinical applications in imaging genomics
Imaging genomics is an emerging data science field that arises with the recent advances in acquiring multimodal imaging data and high throughput omics data. Its major task is to perform integrated analysis of imaging and omics data, often combined with other biomarker, clinical, and environmental data, to gain new insights into the underlying mechanism of human health and disease, which in turn will impact the development of new diagnostic, therapeutic and preventative approaches. Given the unprecedented scale, complexity and heterogeneity of the fast-growing big data in imaging geomics, we are facing major computational, statistical and analytical challenges that have to be met to realize the full potential of these valuable data.
The objective of this Research Topic is to foster new methodologies that could overcome the above challenges. We welcome submissions to propose new effective and efficient methods for analyzing big data in imaging genomics, and yield promising biomedical discoveries to better understand the biological pathways and mechanisms from genetic determinants, molecular and cellular signatures, tissue and organ level biomarkers, and to phenotypical outcomes. Topics include but are not limited to:
• Genetic or epistatic analysis of imaging phenotypes
• Genomic or multi-omics analysis of imaging phenotypes
• Predictive modeling via integrative imaging genomics
• Statistical methods and causal reasoning in imaging genomics
• Machine learning and deep learning in imaging genomics
• Collaborative or federated learning in imaging genomics
• Big data analytics in imaging genomics
• Biomarker discovery in imaging genomics
• Systems biology in imaging genomics
• Translational imaging genomics
• Precision medicine in imaging genomics
• Clinical applications in imaging genomics
