Miao Shidi, Sun Mengzhuo, Li Xuemeng, Wang Mingxuan, Jiang Yuyang, Liu Zengyao, Wang Qiujun, Ding Xuemei, Wang Ruitao
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China (S.M., M.S., M.W., Y.J.).
Department of Internal Medicine, Harbin Medical University Cancer Hospital, Harbin Medical University, Harbin, China (X.L., R.W.).
Acad Radiol. 2025 Jul 23. doi: 10.1016/j.acra.2025.07.015.
Accurate preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) remains challenging. Current imaging biomarkers show limited predictive performance.
To develop a deep learning model based on preoperative multiphase CT images of tumors and lesser omental adipose tissue (LOAT) for predicting MVI status and to analyze associated survival outcomes.
This retrospective study included pathologically confirmed HCC patients from two medical centers between 2016 and 2023. A dual-branch feature fusion model based on ResNet18 was constructed, which extracted fused features from dual-phase CT images of both tumors and LOAT. The model's performance was evaluated on both internal and external test sets. Logistic regression was used to identify independent predictors of MVI. Based on MVI status, patients in the training, internal test, and external test cohorts were stratified into high- and low-risk groups, and overall survival differences were analyzed.
The model incorporating LOAT features outperformed the tumor-only modality, achieving an AUC of 0.889 (95% CI: [0.882, 0.962], P=0.004) in the internal test set and 0.826 (95% CI: [0.793, 0.872], P=0.006) in the external test set. Both results surpassed the independent diagnoses of three radiologists (average AUC=0.772). Multivariate logistic regression confirmed that maximum tumor diameter and LOAT area were independent predictors of MVI. Further Cox regression analysis showed that MVI-positive patients had significantly increased mortality risks in both the internal test set (Hazard Ratio [HR]=2.246, 95% CI: [1.088, 4.637], P=0.029) and external test set (HR=3.797, 95% CI: [1.262, 11.422], P=0.018).
This study is the first to use a deep learning framework integrating LOAT and tumor imaging features, improving preoperative MVI risk stratification accuracy. Independent prognostic value of LOAT has been validated in multicenter cohorts, highlighting its potential to guide personalized surgical planning.
肝细胞癌（HCC）微血管侵犯（MVI）的术前准确预测仍然具有挑战性。目前的影像学生物标志物的预测性能有限。
基于肿瘤和小网膜脂肪组织（LOAT）的术前多期CT图像开发一种深度学习模型，以预测MVI状态并分析相关的生存结果。
这项回顾性研究纳入了2016年至2023年间来自两个医疗中心的病理确诊HCC患者。构建了一种基于ResNet18的双分支特征融合模型，该模型从肿瘤和LOAT的双期CT图像中提取融合特征。在内部和外部测试集上评估该模型的性能。使用逻辑回归来确定MVI的独立预测因素。根据MVI状态，将训练、内部测试和外部测试队列中的患者分为高风险和低风险组，并分析总生存差异。
纳入LOAT特征的模型优于仅基于肿瘤的模型，在内部测试集中的AUC为0.889（95%CI：[0.882, 0.962]，P = 0.004），在外部测试集中为0.826（95%CI：[0.793, 0.872]，P = 0.006）。这两个结果均超过了三位放射科医生的独立诊断（平均AUC = 0.772）。多变量逻辑回归证实，肿瘤最大直径和LOAT面积是MVI的独立预测因素。进一步的Cox回归分析表明，MVI阳性患者在内部测试集（风险比[HR] = 2.246，95%CI：[1.088, 4.637]，P = 0.029）和外部测试集（HR = 3.797，95%CI：[1.262, 11.422]，P = 0.018）中的死亡风险均显著增加。
本研究首次使用整合LOAT和肿瘤影像特征的深度学习框架，提高了术前MVI风险分层的准确性。LOAT的独立预后价值已在多中心队列中得到验证，突出了其指导个性化手术规划的潜力。
