Department of Radiology, Hôpital Beaujon, 100 Boulevard du Général Leclerc, 92110, Clichy, France.
Section of Radiology-BiND, University Hospital 'Paolo Giaccone', Palermo, Italy.
Eur Radiol. 2023 Nov;33(11):7618-7628. doi: 10.1007/s00330-023-09852-1. Epub 2023 Jun 20.
To measure the performance and variability of a radiomics-based model for the prediction of microvascular invasion (MVI) and survival in patients with resected hepatocellular carcinoma (HCC), simulating its sequential development and application.
This study included 230 patients with 242 surgically resected HCCs who underwent preoperative CT, of which 73/230 (31.7%) were scanned in external centres. The study cohort was split into training set (158 patients, 165 HCCs) and held-out test set (72 patients, 77 HCCs), stratified by random partitioning, which was repeated 100 times, and by a temporal partitioning to simulate the sequential development and clinical use of the radiomics model. A machine learning model for the prediction of MVI was developed with least absolute shrinkage and selection operator (LASSO). The concordance index (C-index) was used to assess the value to predict the recurrence-free (RFS) and overall survivals (OS).
In the 100-repetition random partitioning cohorts, the radiomics model demonstrated a mean AUC of 0.54 (range 0.44-0.68) for the prediction of MVI, mean C-index of 0.59 (range 0.44-0.73) for RFS, and 0.65 (range 0.46-0.86) for OS in the held-out test set. In the temporal partitioning cohort, the radiomics model yielded an AUC of 0.50 for the prediction of MVI, a C-index of 0.61 for RFS, and 0.61 for OS, in the held-out test set.
The radiomics models had a poor performance for the prediction of MVI with a large variability in the model performance depending on the random partitioning. Radiomics models demonstrated good performance in the prediction of patient outcomes.
Patient selection within the training set strongly influenced the performance of the radiomics models for predicting microvascular invasion; therefore, a random approach to partitioning a retrospective cohort into a training set and a held-out set seems inappropriate.
• The performance of the radiomics models for the prediction of microvascular invasion and survival widely ranged (AUC range 0.44-0.68) in the randomly partitioned cohorts. • The radiomics model for the prediction of microvascular invasion was unsatisfying when trying to simulate its sequential development and clinical use in a temporal partitioned cohort imaged with a variety of CT scanners. • The performance of the radiomics models for the prediction of survival was good with similar performances in the 100-repetition random partitioning and temporal partitioning cohorts.
测量基于放射组学的模型在预测接受肝切除术的肝细胞癌（HCC）患者微血管侵犯（MVI）和生存方面的性能和可变性，模拟其序贯发展和应用。
本研究纳入了 230 例接受 242 例 HCC 切除术的患者，其中 73/230（31.7%）在外部中心进行了扫描。研究队列按随机分区分为训练集（158 例患者，165 例 HCC）和验证集（72 例患者，77 例 HCC），通过随机分区重复 100 次，并通过时间分区模拟放射组学模型的序贯发展和临床应用。使用最小绝对值收缩和选择算子（LASSO）开发了用于预测 MVI 的机器学习模型。使用一致性指数（C-index）评估预测无复发生存（RFS）和总生存（OS）的价值。
在 100 次重复随机分区队列中，放射组学模型对 MVI 的预测平均 AUC 为 0.54（范围 0.44-0.68），在验证集的 RFS 中的平均 C-index 为 0.59（范围 0.44-0.73），OS 中的平均 C-index 为 0.65（范围 0.46-0.86）。在时间分区队列中，放射组学模型在验证集中对 MVI 的预测 AUC 为 0.50，RFS 的 C-index 为 0.61，OS 的 C-index 为 0.61。
放射组学模型在预测 MVI 方面表现不佳，模型性能的可变性很大，取决于随机分区。放射组学模型在预测患者结局方面表现良好。
在训练集中对患者进行选择会强烈影响放射组学模型预测微血管侵犯的性能；因此，随机方法将回顾性队列分为训练集和验证集似乎不合适。
• 在随机分区的队列中，预测 MVI 和生存的放射组学模型的性能差异很大（AUC 范围为 0.44-0.68）。• 当试图在时间分区队列中模拟其序贯发展和临床应用时，用于预测微血管侵犯的放射组学模型表现并不理想，该队列使用各种 CT 扫描仪成像。• 预测生存的放射组学模型的性能良好，在 100 次重复随机分区和时间分区队列中的表现相似。
