Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu Province 215006, PR China.
Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu Province 215006, PR China; Institute of Medical Imaging, Soochow University, Suzhou, Jiangsu Province 215006, PR China.
Eur J Radiol. 2022 Oct;155:110437. doi: 10.1016/j.ejrad.2022.110437. Epub 2022 Jul 8.
To establish a radiomics nomogram for preoperative prediction of Ki-67 proliferation index in stage T1a-b lung adenocarcinoma.
A total of 206 patients with pathologically confirmed lung adenocarcinoma who underwent CT scans within 2 weeks preoperatively from January 2016 to June 2020 were retrospectively included. Ki-67 index ≤ 10% was considered low expression, and Ki-67 index > 10% was considered high expression. The primary cohort was randomized with a 7:3 ratio into a training cohort (n = 145) and a validation cohort (n = 61). The minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) were used for feature selection, and radiomics signature was constructed. Univariate and multivariate logistic regression analyses were used to identify clinically important risk factors and radiomics signature associated with Ki-67 proliferation index, which were then combined into radiomics nomogram.
Tumor maximum diameter (P = 0.005), lobulation (P = 0.002), absent of vacuole (P < 0.001), and Radscore (P < 0.001) were independent risk predictors of high Ki-67 proliferation index expression. The radiomics nomogram showed good predictive efficacy. The AUC, sensitivity, specificity and accuracy of radiomics nomogram in the training and validation cohorts were 0.91 (95% CI: 0.86-0.96), 87.9%, 80.5%, 83.4% and 0.85 (95% CI: 0.75-0.94), 71.9%, 82.8% and 77.0%. Decision curve analysis further demonstrated the clinical utility of the nomogram.
Radiomics nomogram provide a non-invasive method to predict Ki-67 proliferation index preoperatively in stage T1a-b lung adenocarcinoma, which might be the supplementary information for clinicians to choose the appropriate treatment program.
建立用于术前预测 T1a-b 期肺腺癌 Ki-67 增殖指数的放射组学列线图。
回顾性纳入 206 例 2016 年 1 月至 2020 年 6 月期间术前 2 周内行 CT 扫描且经病理证实为肺腺癌的患者。Ki-67 指数≤10%为低表达，Ki-67 指数＞10%为高表达。原始队列按照 7∶3 的比例随机分为训练集（n=145）和验证集（n=61）。采用最小冗余最大相关性（mRMR）和最小绝对收缩和选择算子（LASSO）进行特征选择，构建放射组学特征。采用单因素和多因素逻辑回归分析确定与 Ki-67 增殖指数相关的临床重要风险因素和放射组学特征，然后将其组合成放射组学列线图。
肿瘤最大直径（P=0.005）、分叶（P=0.002）、无空泡（P＜0.001）和 Radscore（P＜0.001）是 Ki-67 增殖指数高表达的独立危险因素。放射组学列线图具有良好的预测效能。在训练集和验证集中，放射组学列线图的 AUC、敏感性、特异性和准确性分别为 0.91（95%CI：0.860.96）、87.9%、80.5%和 83.4%和 0.85（95%CI：0.750.94）、71.9%、82.8%和 77.0%。决策曲线分析进一步证明了该列线图的临床实用性。
放射组学列线图提供了一种术前预测 T1a-b 期肺腺癌 Ki-67 增殖指数的非侵入性方法，可能为临床医生选择合适的治疗方案提供补充信息。
