深度学习辅助鉴别肝细胞癌与局灶性肝脏病变:四期与三期CT成像方案的选择
回顾性纳入342例患者共449个局灶性肝脏病变,训练三种卷积稠密网络分别基于四期CT(模型A)、无门静脉期三期CT(模型B)和无平扫三期CT(模型C)鉴别肝细胞癌与非肝细胞癌。测试集诊断准确率模型A为83.3%、模型B为81.1%、模型C为85.6%,AUC分别为0.925、0.862、0.920;模型A与C的AUC无显著差异(p=0.765),模型A与B(p=0.038)及B与C(p=0.028)有显著差异。结论提示联合卷积稠密网络时,去除平扫期的三期CT方案与四期方案诊断准确率相似,可能通过去除平扫期优化多期CT方案以减少辐射剂量。
要点
- 联合卷积稠密网络时,无平扫三期CT(模型C)与四期CT(模型A)鉴别肝细胞癌的AUC无显著差异(p=0.765)。
- 模型C测试集诊断准确率85.6%、AUC 0.920,模型A分别为83.3%和0.925。
- 模型B(无门静脉期)AUC 0.862,显著低于模型A(p=0.038)和模型C(p=0.028)。
核心结论
- 联合卷积稠密网络时,去除平扫期的三期CT方案与四期方案在鉴别肝细胞癌与其他局灶性肝脏病变方面诊断准确率相似,提示可通过去除平扫期优化多期CT方案以减少辐射剂量。
研究设计与样本
- 回顾性纳入342例患者(平均年龄49.1±10.5岁,范围19-86岁,男性占65.8%),均接受四期CT方案(平扫、动脉期、门静脉期和延迟期)扫描。
- 共449个局灶性肝脏病变,依据最佳可用参考标准分为肝细胞癌组和非肝细胞癌组。
- 训练三种卷积稠密网络:模型A输入四期CT图像,模型B输入无门静脉期的三期图像,模型C输入无平扫期的三期图像;80%病变用于训练,其余20%用于测试。
- 采用受试者工作特征曲线和混淆矩阵分析评估,DeLong检验比较模型A与B、B与C、A与C的曲线下面积(AUC)。
诊断标准与关键数值
- 测试集鉴别肝细胞癌与其他局灶性肝脏病变的诊断准确率:模型A为83.3%,模型B为81.1%,模型C为85.6%。
- 测试集AUC:模型A为0.925,模型B为0.862,模型C为0.920。
- 模型A与C的AUC无显著差异(p=0.765);模型A与B的AUC有显著差异(p=0.038);模型B与C的AUC有显著差异(p=0.028)。
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: To evaluate whether a three-phase dynamic contrast-enhanced CT protocol, when combined with a deep learning model, has similar accuracy in differentiating hepatocellular carcinoma (HCC) from other focal liver lesions (FLLs) compared with a four-phase protocol.
METHODS: Three hundred and forty-two patients (mean age 49.1 ± 10.5 years, range 19-86 years, 65.8% male) scanned with a four-phase CT protocol (precontrast, arterial, portal-venous and delayed phases) were retrospectively enrolled. A total of 449 FLLs were categorized into HCC and non-HCC groups based on the best available reference standard. Three convolutional dense networks (CDNs) with the input of four-phase CT images (model A), three-phase images without portal-venous phase (model B) and three-phase images without precontrast phase (model C) were trained on 80% of lesions and evaluated in the other 20% by receiver operating characteristics (ROC) and confusion matrix analysis. The DeLong test was performed to compare the areas under the ROC curves (AUCs) of A with B, B with C, and A with C.
RESULTS: The diagnostic accuracy in differentiating HCC from other FLLs on test sets was 83.3% for model A, 81.1% for model B and 85.6% for model C, and the AUCs were 0.925, 0.862 and 0.920, respectively. The AUCs of models A and C did not differ significantly (p = 0.765), but the AUCs of models A and B (p = 0.038) and of models B and C (p = 0.028) did.
CONCLUSIONS: When combined with a CDN, a three-phase CT protocol without precontrast showed similar diagnostic accuracy as a four-phase protocol in differentiating HCC from other FLLs, suggesting that the multiphase CT protocol for HCC diagnosis might be optimized by removing the precontrast phase to reduce radiation dose.
引用
- Shi W, Kuang S, Cao S, et al. Deep learning assisted differentiation of hepatocellular carcinoma from focal liver lesions: choice of four-phase and three-phase CT imaging protocol. Abdom Radiol (NY). 2020. PMID: 32232524. doi:10.1007/s00261-020-02485-8
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。