Department of Radiology, Jiangsu Key Laboratory of Molecular and Functional Imaging, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.
Hepatic-Biliary-Pancreatic Center, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.
Ann Surg Oncol. 2022 May;29(5):2960-2970. doi: 10.1245/s10434-022-11346-1. Epub 2022 Jan 31.
Prediction models with or without radiomic analysis for microvascular invasion (MVI) in hepatocellular carcinoma (HCC) have been reported, but the potential for model-predicted MVI in surgical planning is unclear. Therefore, we aimed to explore the effect of predicted MVI on early recurrence after anatomic resection (AR) and non-anatomic resection (NAR) to assist surgical strategies.
Patients with a single HCC of 2-5 cm receiving curative resection were enrolled from 2 centers. Their data were used to develop (n = 230) and test (n = 219) two prediction models for MVI using clinical factors and preoperative computed tomography images. The two prediction models, clinico-radiologic model and clinico-radiologic-radiomic (CRR) model (clinico-radiologic variables + radiomic signature), were compared using the Delong test. Early recurrence based on model-predicted high-risk MVI was evaluated between AR (n = 118) and NAR (n = 85) via propensity score matching using patient data from another 2 centers for external validation.
The CRR model showed higher area under the curve values (0.835-0.864 across development, test, and external validation) but no statistically significant improvement over the clinico-radiologic model (0.796-0.828). After propensity score matching, difference in 2-year recurrence between AR and NAR was found in the CRR model predicted high-risk MVI group (P = 0.005) but not in the clinico-radiologic model predicted high-risk MVI group (P = 0.31).
The prediction model incorporating radiomics provided an accurate preoperative estimation of MVI, showing the potential for choosing the more appropriate surgical procedure between AR and NAR.
已有研究报道了包含或不包含放射组学分析的用于预测肝细胞癌（HCC）微血管侵犯（MVI）的预测模型，但模型预测的 MVI 对手术规划的潜在影响尚不清楚。因此，我们旨在探讨预测 MVI 对解剖性切除术（AR）和非解剖性切除术（NAR）后早期复发的影响，以协助制定手术策略。
本研究纳入了来自 2 个中心的因单发 2-5cm HCC 而接受根治性切除术的患者。使用这些患者的数据，我们采用临床因素和术前计算机断层扫描（CT）图像，开发和验证了用于预测 MVI 的两种预测模型，分别为临床放射学模型和临床放射组学（CRR）模型（临床放射学变量+放射组学特征）。采用 Delong 检验比较两种预测模型。采用另外 2 个中心的患者数据进行倾向评分匹配，以外部验证的方式，评估基于模型预测的高危 MVI 的早期复发在 AR（n = 118）和 NAR（n = 85）之间的差异。
CRR 模型的曲线下面积（AUC）值（开发、验证和外部验证时分别为 0.835-0.864）更高，但与临床放射学模型（0.796-0.828）相比，并无统计学意义上的显著改善。在倾向评分匹配后，CRR 模型预测高危 MVI 组中 AR 和 NAR 之间的 2 年复发率差异有统计学意义（P = 0.005），而临床放射学模型预测高危 MVI 组中则无统计学意义（P = 0.31）。
纳入放射组学特征的预测模型可准确预测 MVI，为 AR 和 NAR 之间选择更合适的手术方式提供了潜力。
