Mu Wei, Liang Ying, Hall Lawrence O, Tan Yan, Balagurunathan Yoganand, Wenham Robert, Wu Ning, Tian Jie, Gillies Robert J
Department of Cancer Physiology (W.M., Y.T., Y.B., R.J.G.) and Gynecologic Oncology (R.W.), H. Lee Moffitt Cancer Center and Research Institute, 12902 Magnolia Dr, Tampa, FL 33612; Cancer Institute and Hospital, Chinese Academy of Medical Sciences, Beijing, China (Y.L., N.W.); Department of Computer Science and Engineering, University of South Florida, Tampa, Fla (L.O.H.); Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, China (J.T.); and CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China (J.T.).
Radiol Artif Intell. 2020 Nov 4;2(6):e190218. doi: 10.1148/ryai.2020190218. eCollection 2020 Nov.
To determine if quantitative features extracted from pretherapy fluorine 18 fluorodeoxyglucose (F-FDG) PET/CT estimate prognosis in patients with locally advanced cervical cancer treated with chemoradiotherapy.
In this retrospective study, PET/CT images and outcomes were curated from 154 patients with locally advanced cervical cancer, who underwent chemoradiotherapy from two institutions between March 2008 and June 2016, separated into independent training ( = 78; mean age, 51 years ± 13 [standard deviation]) and testing ( = 76; mean age, 50 years ± 10) cohorts. Radiomic features were extracted from PET, CT, and habitat (subregions with different metabolic characteristics) images that were derived by fusing PET and CT images. Parsimonious sets of these features were identified by the least absolute shrinkage and selection operator analysis and used to generate predictive radiomics signatures for progression-free survival (PFS) and overall survival (OS) estimation. Prognostic validation of the radiomic signatures as independent prognostic markers was performed using multivariable Cox regression, which was expressed as nomograms, together with other clinical risk factors.
The radiomics nomograms constructed with T stage, lymph node status, and radiomics signatures resulted in significantly better performance for the estimation of PFS (Harrell concordance index [C-index], 0.85 for training and 0.82 for test) and OS (C-index, 0.86 for training and 0.82 for test) compared with International Federation of Gynecology and Obstetrics staging system (C-index for PFS, 0.70 for training [ = .001] and 0.70 for test [ = .002]; C-index for OS, 0.73 for training [ < .001] and 0.70 for test [ < .001]), respectively.
Prognostic models were generated and validated from quantitative analysis of F-FDG PET/CT habitat images and clinical data, and may have the potential to identify the patients who need more aggressive treatment in clinical practice, pending further validation with larger prospective cohorts.© RSNA, 2020.
确定从治疗前氟代脱氧葡萄糖（F-FDG）PET/CT中提取的定量特征能否评估接受放化疗的局部晚期宫颈癌患者的预后。
在这项回顾性研究中，收集了2008年3月至2016年6月间在两家机构接受放化疗的154例局部晚期宫颈癌患者的PET/CT图像及预后情况，并将其分为独立的训练组（n = 78；平均年龄51岁±13[标准差]）和测试组（n = 76；平均年龄50岁±10）。从PET、CT以及通过融合PET和CT图像得到的栖息地（具有不同代谢特征的子区域）图像中提取影像组学特征。通过最小绝对收缩和选择算子分析确定这些特征的简约集，并用于生成无进展生存期（PFS）和总生存期（OS）估计的预测影像组学特征。使用多变量Cox回归对影像组学特征作为独立预后标志物进行预后验证，该回归以列线图表示，并结合其他临床风险因素。
与国际妇产科联盟分期系统相比，由T分期、淋巴结状态和影像组学特征构建的影像组学列线图在估计PFS（训练组的Harrell一致性指数[C指数]为0.85，测试组为0.82）和OS（训练组C指数为0.86，测试组为0.82）方面表现明显更好（PFS的C指数，训练组为0.70[P = .001]，测试组为0.70[P = .002]；OS的C指数，训练组为0.73[P < .001]，测试组为0.70[P < .001]）。
通过对F-FDG PET/CT栖息地图像和临床数据进行定量分析，生成并验证了预后模型，在通过更大规模的前瞻性队列进行进一步验证之前，该模型可能有潜力在临床实践中识别出需要更积极治疗的患者。©RSNA，2020年。
