Radiomics outcome prediction in Oropharyngeal cancer

There is an unmet need for integrating quantitative imaging biomarkers into current risk stratification tools and to explore the correlation between radiomics features –alone or in combination with clinical prognosticators- and tumor outcome. Clinical meta-data and matched baseline contrast-enhanced computed tomography (CECT) scans were used to build a cohort of 495 oropharyngeal cancer (OPC) patients treated between 2005 and 2012. Expert radiation oncologists manually segmented primary and nodal disease gross volumes (GTVp & GTVn). Structures were named per the American Association of Physicists in Medicine (AAPM) TG-263 recommendations, then retrieved in RT-STRUCT format. Matched patient, disease, treatment and outcomes data were obtained. Radiomics analysis was performed using an open-source institutionally-developed software that runs on Matlab platform.当前仍存在未被满足的临床需求：将定量成像生物标志物整合至现有风险分层工具中，并探究放射组学（radiomics）特征单独使用或与临床预后因子联合时，与肿瘤转归之间的关联。本研究采用临床元数据与匹配的基线增强计算机断层扫描（contrast-enhanced computed tomography, CECT）影像，构建了一组共495例于2005年至2012年间接受治疗的口咽癌（oropharyngeal cancer, OPC）患者队列。由资深放射肿瘤学家手动勾画原发肿瘤与淋巴结肿瘤大体靶区（gross tumor volume primary, GTVp；gross tumor volume nodal, GTVn）。所有解剖结构均按照美国医学物理学家协会（American Association of Physicists in Medicine, AAPM）TG-263指南的建议进行命名，并以RT-STRUCT格式存储与调取。本研究同步获取了匹配的患者信息、疾病特征、治疗方案及转归数据。本研究采用一款基于Matlab平台开发的开源院内自研软件完成放射组学分析。