放射基因组学
医学
医学物理学
无线电技术
放射科
生物信息学
病理
人工智能
计算机科学
生物
作者
Alexander Lam,Kevin Bui,Eduardo Hernandez Rangel,Michael Nguyentat,D. Fernando,Kari Nelson,Nadine Abi-Jaoudeh
标识
DOI:10.1016/j.jvir.2017.11.021
摘要
Radiogenomics involves the integration of mineable data from imaging phenotypes with genomic and clinical data to establish predictive models using machine learning. As a noninvasive surrogate for a tumor's in vivo genetic profile, radiogenomics may potentially provide data for patient treatment stratification. Radiogenomics may also supersede the shortcomings associated with genomic research, such as the limited availability of high-quality tissue and restricted sampling of tumoral subpopulations. Interventional radiologists are well suited to circumvent these obstacles through advancements in image-guided tissue biopsies and intraprocedural imaging. Comprehensive understanding of the radiogenomic process is crucial for interventional radiologists to contribute to this evolving field.
科研通智能强力驱动
Strongly Powered by AbleSci AI