Department of Radiation Oncology, University of Michigan, Ann Arbor, Michigan.
Icahn Institute for Genomics and Multiscale Biology and Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York.
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1070-1073. doi: 10.1016/j.ijrobp.2018.08.022. Epub 2018 Oct 18.
Recent advances in imaging and biotechnology have tremendously improved the availability of quantitative imaging (radiomics) and molecular data (radiogenomics) for radiotherapy patients. This big data development with its comprehensive nature promises to transform outcome modeling in radiotherapy from few dose-volume metrics into utilizing more data-driven analytics. However, it also presents new profound challenges and creates new tasks for alleviating uncertainties arising from dealing with heterogeneous data and complex big data analytics. Therefore, more rigorous validation procedures need to be devised for these radiomics/radiogenomics models compared to traditional outcome modeling approaches previously utilized in radiation oncology, before they can be safely deployed for clinical trials or incorporated into daily practice. This editorial highlights current affairs, identifies some of the frequent sources of uncertainties, and presents some of the recommended practices for radiomics/radiogenomics models’ evaluation and validation.
近年来，影像学和生物技术的进步极大地提高了放射治疗患者的定量成像（放射组学）和分子数据（放射基因组学）的可用性。这种大数据的发展具有综合性，有望将放射治疗的结果建模从少数剂量-体积指标转变为利用更多数据驱动的分析。然而，它也带来了新的深刻挑战，并为减轻处理异质数据和复杂大数据分析所带来的不确定性创造了新的任务。因此，与之前在肿瘤放射学中使用的传统结果建模方法相比，这些放射组学/放射基因组学模型需要设计更严格的验证程序，然后才能安全地用于临床试验或纳入日常实践。本社论强调了当前的情况，确定了一些常见的不确定性来源，并提出了一些用于放射组学/放射基因组学模型评估和验证的推荐实践。
