Department of Radiology, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, 150 Ximen St, Linhai, Taizhou, 317000, Zhejiang, China.
Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
Abdom Radiol (NY). 2024 Apr;49(4):1074-1083. doi: 10.1007/s00261-023-04141-3. Epub 2024 Jan 4.
This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC).
320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis.
Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05).
A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.
本研究旨在构建和评估一种深度学习（DL）模型，以预测肝细胞癌（HCC）患者术前的肿瘤簇包绕血管（VETC）和预后。
本回顾性研究纳入了来自两家医院的 320 例经病理证实的 HCC 患者（58 名女性和 262 名男性）。机构 1（n=219）和机构 2（n=101）分别作为训练和外部测试队列。使用动脉期、门静脉期和延迟期（AP、PP 和 DP）对肿瘤进行三维评估，并手动对感兴趣区域进行分割。开发了三个基于 ResNet-34 的深度学习模型，包括三个基于单个序列的模型。融合模型通过将三个单序列模型的输出预测概率输入逻辑回归来构建。使用受试者工作特征曲线下的面积（AUC）来比较性能，并使用 Delong 检验比较 AUC。早期复发（ER）定义为手术后两年内复发，通过 Kaplan-Meier 生存分析评估早期无复发生存率（ERFS）。
在 320 例 HCC 患者中，227 例为 VETC-，93 例为 VETC+。在外部测试队列中，融合模型的 AUC 为 0.772，灵敏度为 0.80，特异性为 0.61。融合模型预测的高危和低危 VETC 类别在 ERFS 率方面存在显著差异，与通过病理分析确定的 VETC+和 VETC-的结果相似（p<0.05）。
基于 ResNet-34 的深度学习框架在促进 VETC 的非侵入性预测以及患者预后方面具有潜力。
