文献速递腹部MR

基于MRI的深度学习模型预测肝细胞癌肿瘤簇包裹血管及预后

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma.
PubMed 文献 · Abdom Radiol (NY) · 2024-01-04

本研究回顾性纳入两家医院320例经病理确诊的肝细胞癌患者,以机构1(219例)为训练队列、机构2(101例)为外部测试队列,基于动脉期、门静脉期和延迟期MRI构建三个ResNet-34单序列模型,并以逻辑回归融合其输出概率。外部测试队列中融合模型预测VETC的AUC为0.772、敏感度0.80、特异度0.61,基于融合模型划分的VETC高风险与低风险组早期无复发生存率差异有统计学意义(P<0.05)。

要点

  • 融合模型在外部测试队列预测VETC的AUC为0.772、敏感度0.80、特异度0.61。
  • 融合模型划分的VETC高风险与低风险组早期无复发生存率差异有统计学意义(P<0.05)。
  • VETC+与VETC-病理分组间早期无复发生存率同样存在显著差异(P<0.05)。

核心结论

  • 基于ResNet-34的深度学习框架在无创预测VETC及患者预后方面显示出潜力。

研究设计与样本

  • 回顾性研究,纳入两家医院320例经病理确诊的肝细胞癌患者(女58例、男262例),机构1(n=219)为训练队列、机构2(n=101)为外部测试队列。

关键影像表现/征象

  • 肿瘤采用三维评估,在动脉期、门静脉期和延迟期手动勾画感兴趣区。
  • 基于动脉期、门静脉期和延迟期分别构建三个ResNet-34单序列模型。
  • 融合模型将三个单序列模型输出的预测概率输入逻辑回归构建。
  • 外部测试队列中融合模型预测VETC的AUC为0.772、敏感度0.80、特异度0.61。
  • 320例中VETC- 227例、VETC+ 93例。

诊断标准与关键数值

  • VETC预测性能以受试者工作特征曲线下面积(AUC)评价,AUC比较采用Delong检验。
  • 外部测试队列融合模型预测VETC的AUC为0.772、敏感度0.80、特异度0.61。
  • 早期复发定义为手术后两年内复发,早期无复发生存率采用Kaplan-Meier生存分析评估。

临床应用与阅片要点

  • 融合模型预测的VETC高风险与低风险类别间早期无复发生存率差异有统计学意义(P<0.05),与病理证实的VETC+和VETC-结果相似。
  • 作者结论认为基于ResNet-34的深度学习框架在无创预测VETC及患者预后方面显示出潜力。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: 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).

METHODS: 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.

RESULTS: 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).

CONCLUSIONS: A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Yang J, Dong X, Wang F, et al. A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma. Abdom Radiol (NY). 2024. PMID: 38175256. doi:10.1007/s00261-023-04141-3

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。