This study aimed to evaluate the potential of pre-treatment CT-based radiomics features (RFs) derived from single and multiple tumor sites, and state-of-the-art machine-learning survival algorithms, in predicting progression-free survival (PFS) for patients with metastatic lung adenocarcinoma (MLUAD) receiving first-line treatment including immune checkpoint inhibitors (CPIs). To do so, all adults with newly diagnosed MLUAD, pre-treatment contrast-enhanced CT scan, and performance status ≤ 2 who were treated at our cancer center with first-line CPI between November 2016 and November 2022 were included. RFs were extracted from all measurable lesions with a volume ≥ 1 cm3on the CT scan. To capture intra- and inter-tumor heterogeneity, RFs from the largest tumor of each patient, as well as lowest, highest, and average RF values over all lesions per patient were collected. Intra-patient inter-tumor heterogeneity metrics were calculated to measure the similarity between each patient lesions. After filtering predictors with univariable Coxp< 0.100 and analyzing their correlations, five survival machine-learning algorithms (stepwise Cox regression [SCR], LASSO Cox regression, random survival forests, gradient boosted machine [GBM], and deep learning [Deepsurv]) were trained in 100-times repeated 5-fold cross-validation (rCV) to predict PFS on three inputs: (i) clinicopathological variables, (ii) all radiomics-based and clinicopathological (full input), and (iii) uncorrelated radiomics-based and clinicopathological variables (uncorrelated input). The Models’ performances were evaluated using the concordance index (c-index). Overall, 140 patients were included (median age: 62.5 years, 36.4% women). In rCV, the highest c-index was reached with Deepsurv (c-index = 0.631, 95%CI = 0.625–0.647), followed by GBM (c-index = 0.603, 95%CI = 0.557–0.646), significantly outperforming standard SCR whatever its input (c-index range: 0.560–0.570, allp< 0.0001). Thus, single- and multi-site pre-treatment radiomics data provide valuable prognostic information for predicting PFS in MLUAD patients undergoing first-line CPI treatment when analyzed with advanced machine-learning survival algorithms.
本研究旨在评估基于治疗前CT影像组学特征（RFs）的潜力，这些特征来源于单个及多个肿瘤部位，并结合先进的机器学习生存算法，用于预测接受一线免疫检查点抑制剂（CPIs）治疗的转移性肺腺癌（MLUAD）患者的无进展生存期（PFS）。为此，我们纳入了2016年11月至2022年11月期间在我中心接受一线CPI治疗的所有新诊断MLUAD成年患者，这些患者均具备治疗前增强CT扫描资料且体能状态评分≤2。从CT扫描中所有体积≥1 cm³的可测量病灶中提取RFs。为捕捉肿瘤内及肿瘤间的异质性，我们收集了每位患者最大病灶的RFs，以及每位患者所有病灶中RFs的最低值、最高值和平均值。计算了患者内肿瘤间异质性指标，以衡量每位患者各病灶间的相似性。在通过单变量Cox分析（p<0.100）筛选预测因子并分析其相关性后，采用五种生存机器学习算法（逐步Cox回归[SCR]、LASSO Cox回归、随机生存森林、梯度提升机[GBM]和深度学习[Deepsurv]）进行100次重复的5折交叉验证（rCV），基于三种输入数据预测PFS：（i）临床病理变量，（ii）所有影像组学及临床病理变量（完整输入），（iii）无相关性的影像组学及临床病理变量（无相关性输入）。使用一致性指数（c-index）评估模型性能。共纳入140例患者（中位年龄62.5岁，女性占36.4%）。在rCV中，Deepsurv获得最高c-index（c-index=0.631，95%CI=0.625–0.647），其次为GBM（c-index=0.603，95%CI=0.557–0.646），无论输入数据为何，这两种算法均显著优于标准SCR（c-index范围：0.560–0.570，所有p<0.0001）。因此，当采用先进的机器学习生存算法进行分析时，基于单病灶及多病灶的治疗前影像组学数据能为接受一线CPI治疗的MLUAD患者提供有价值的PFS预测信息。
肿瘤(癌症)患者之家