Department of Radiology, Zhongshan Hospital, Fudan University, No.180 Fenglin Rd, Shanghai, 200032, China.
Shanghai Institute of Medical Imaging, No.180 Fenglin Rd, Shanghai, 200032, China.
Radiol Med. 2023 Mar;128(3):274-288. doi: 10.1007/s11547-023-01597-7. Epub 2023 Feb 11.
Incidence and mortality of intrahepatic cholangiocarcinoma (ICC) have been increasing over the past few decades, and Ki67 is an adverse prognostic predictor and an attractive therapeutic target for ICC patients. Thus, we aim to develop and validate a combined Ki67 prediction model for ICC patients.
Preoperative contrast-enhanced MR images were collected from 178 patients with postoperative pathologically confirmed ICC, and randomly divided into training and validation cohorts in a ratio of 7:3 (124:54). A time-independent test cohort of 49 ICC patients was used for validation. Independent clinicoradiological features of Ki67 status were determined by multivariate analysis. Optimal radiomics features were selected by least absolute shrinkage and selection operator logistic regression and linear discriminant analysis was used to construct combined models. The prediction efficacy of combined model was assessed by receiver operating characteristics curve, and verified by its calibration, decision and clinical impact curves.
HBV (p = 0.022), arterial rim enhancement (p = 0.006) and enhancement pattern (p = 0.012) are independent clinicoradiological features. The radiomics model achieves good prediction efficacy in the training cohort (AUC = 0.860) and validation cohort (AUC = 0.843). The combined Ki67 prediction model incorporates clinicoradiological and radiomics features, and it yields desirable predictive efficiency in test cohort (AUC = 0.815). Decision curves and clinical impact curves further validate that the combined Ki67 prediction model can achieve net benefits in clinical work.
The combined Ki67 model incorporating HBV, arterial rim enhancement, enhancement pattern and radiomics features is a potential biomarker in Ki67 prediction and stratification.
在过去几十年中，肝内胆管癌（ICC）的发病率和死亡率一直在上升，Ki67 是 ICC 患者不良预后的预测因子和有吸引力的治疗靶点。因此，我们旨在开发和验证 ICC 患者的 Ki67 联合预测模型。
从 178 例经术后病理证实为 ICC 的患者中收集术前增强磁共振成像（MRI）资料，并按 7：3 的比例（124：54）随机分为训练集和验证集。使用 49 例 ICC 患者的时间独立测试队列进行验证。通过多变量分析确定 Ki67 状态的独立临床影像学特征。通过最小绝对收缩和选择算子逻辑回归选择最佳的放射组学特征，并使用线性判别分析构建联合模型。通过接收者操作特征曲线评估联合模型的预测效能，并通过其校准、决策和临床影响曲线进行验证。
HBV（p=0.022）、动脉边缘增强（p=0.006）和增强模式（p=0.012）是独立的临床影像学特征。放射组学模型在训练队列（AUC=0.860）和验证队列（AUC=0.843）中具有良好的预测效能。联合 Ki67 预测模型结合了临床影像学和放射组学特征，在测试队列中具有理想的预测效率（AUC=0.815）。决策曲线和临床影响曲线进一步验证了联合 Ki67 预测模型在临床工作中可以获得净收益。
联合 Ki67 模型纳入 HBV、动脉边缘增强、增强模式和放射组学特征，是 Ki67 预测和分层的潜在生物标志物。
