Université Paris Saclay, INSERM UMR1030, Gustave Roussy, 94805, Villejuif, France.
Department of Radiation Oncology, Gustave Roussy, F-94805, Villejuif, France.
Eur J Nucl Med Mol Imaging. 2023 Nov;50(13):4010-4023. doi: 10.1007/s00259-023-06320-2. Epub 2023 Aug 26.
Locally advanced cervical cancer (LACC) and anal and oropharyngeal squamous cell carcinoma (ASCC and OPSCC) are mostly caused by oncogenic human papillomaviruses (HPV). In this paper, we developed machine learning (ML) models based on clinical, biological, and radiomic features extracted from pre-treatment fluorine-18-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET) images to predict the survival of patients with HPV-induced cancers. For this purpose, cohorts from five institutions were used: two cohorts of patients treated for LACC including 104 patients from Gustave Roussy Campus Cancer (Center 1) and 90 patients from Leeds Teaching Hospitals NHS Trust (Center 2), two datasets of patients treated for ASCC composed of 66 patients from Institut du Cancer de Montpellier (Center 3) and 67 patients from Oslo University Hospital (Center 4), and one dataset of 45 OPSCC patients from the University Hospital of Zurich (Center 5). Radiomic features were extracted from baseline [18F]-FDG PET images. The ComBat technique was applied to mitigate intra-scanner variability. A modified consensus nested cross-validation for feature selection and hyperparameter tuning was applied on four ML models to predict progression-free survival (PFS) and overall survival (OS) using harmonized imaging features and/or clinical and biological variables as inputs. Each model was trained and optimized on Center 1 and Center 3 cohorts and tested on Center 2, Center 4, and Center 5 cohorts. The radiomic-based CoxNet model achieved C-index values of 0.75 and 0.78 for PFS and 0.76, 0.74, and 0.75 for OS on the test sets. Radiomic feature-based models had superior performance compared to the bioclinical ones, and combining radiomic and bioclinical variables did not improve the performances. Metabolic tumor volume (MTV)-based models obtained lower C-index values for a majority of the tested configurations but quite equivalent performance in terms of time-dependent AUCs (td-AUC). The results demonstrate the possibility of identifying common PET-based image signatures for predicting the response of patients with induced HPV pathology, validated on multi-center multiconstructor data.
局部晚期宫颈癌（LACC）和肛门及口咽鳞状细胞癌（ASCC 和 OPSCC）主要由致癌人乳头瘤病毒（HPV）引起。在本文中，我们基于预处理氟-18-氟代脱氧葡萄糖正电子发射断层扫描（[18F]-FDG PET）图像中提取的临床、生物学和放射组学特征开发了机器学习（ML）模型，以预测 HPV 诱导的癌症患者的生存情况。为此，我们使用了来自五个机构的队列：两个治疗 LACC 的患者队列，包括来自古斯塔夫·鲁西癌症中心（中心 1）的 104 名患者和来自利兹教学医院 NHS 信托基金（中心 2）的 90 名患者；两个治疗 ASCC 的患者数据集，包括来自蒙彼利埃癌症研究所（中心 3）的 66 名患者和来自奥斯陆大学医院（中心 4）的 67 名患者；以及来自苏黎世大学医院（中心 5）的 45 名 OPSCC 患者数据集。从基线 [18F]-FDG PET 图像中提取放射组学特征。应用 ComBat 技术减轻扫描仪内变异性。在四个 ML 模型上应用经过修改的共识嵌套交叉验证来进行特征选择和超参数调整，以使用协调成像特征和/或临床和生物学变量作为输入来预测无进展生存期（PFS）和总生存期（OS）。每个模型都在中心 1 和中心 3 队列上进行训练和优化，并在中心 2、中心 4 和中心 5 队列上进行测试。基于放射组学的 CoxNet 模型在测试集中的 PFS 和 OS 的 C 指数值分别为 0.75 和 0.78。基于放射组学特征的模型比生物临床模型的性能更好，并且结合放射组学和生物临床变量并没有提高性能。代谢肿瘤体积（MTV）-基于模型的大多数测试配置获得较低的 C 指数值，但在时间依赖性 AUC（td-AUC）方面的性能相当。这些结果证明了在多中心多构造器数据上验证的识别用于预测 HPV 诱导病理学患者反应的常见 PET 基于图像特征的可能性。
