整合超声造影时空成像与临床数据的深度学习模型用于肝细胞癌与肝内胆管癌的鉴别诊断
该回顾性研究分析了165例肝内胆管癌与140例日期匹配的肝细胞癌患者的超声造影数据(造影剂为SonoVue®六氟化硫微泡),开发了CEUS-CD-Net深度学习模型提取动态超声造影的时空特征并结合临床参数。测试队列中模型AUC为0.884(95%CI 0.794-0.938),优于仅基于动态超声造影的CEUS-Net(0.827)、仅基于临床数据的CD-Net(0.812)、静态图像模型sCEUS-Net(0.772)及时间-强度曲线模型TIC-Model(0.731),在确定病例亚组中AUC为0.893,优于放射科医师评估的0.790。
要点
- CEUS-CD-Net在测试队列鉴别肝细胞癌与肝内胆管癌的AUC为0.884(95%CI 0.794-0.938)。
- 模型在确定病例亚组AUC为0.893(95%CI 0.806-0.950),优于放射科医师评估的0.790(95%CI 0.683-0.868)。
- 模型可视化显示CEUS-CD-Net在辨识超声造影细微模式方面超过放射科医师。
核心结论
- 整合动态超声造影的空间与时间特征及患者临床参数可显著改善肝细胞癌与肝内胆管癌的鉴别诊断。
研究设计与样本
- 回顾性分析165例肝内胆管癌患者和140例日期匹配的肝细胞癌患者的超声造影数据,造影剂为SonoVue®六氟化硫微泡,开发CEUS-CD-Net深度学习模型并与单源数据模型、静态图像模型、时间-强度曲线模型及放射科医师评估比较。
诊断标准与关键数值
- 测试队列中CEUS-CD-Net鉴别肝细胞癌与肝内胆管癌的AUC为0.884(95%CI 0.794-0.938),高于CEUS-Net的0.827(95%CI 0.730-0.896)、CD-Net的0.812(95%CI 0.718-0.887)、sCEUS-Net的0.772(95%CI 0.669-0.851)和TIC-Model的0.731(95%CI 0.633-0.823)。
临床应用与阅片要点
- 模型可视化结果提示CEUS-CD-Net在辨识超声造影反映的细微模式方面超过放射科医师,可用于辅助肝细胞癌与肝内胆管癌的鉴别诊断。
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 develop a deep learning model, capable of extracting both spatial and temporal features from contrast-enhanced ultrasound (CEUS) data and integrating with patient clinical parameters, for the differential diagnosis between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC).
MATERIALS AND METHODS: We retrospectively analyzed the CEUS data (ultrasound contrast agent: SonoVue®-sulfur hexafluoride microbubbles) from 165 ICC patients and 140 date-matched HCC patients. A deep learning model, namely CEUS-CD-Net, was developed to extract spatial-temporal features from dynamic CEUS data and integrate them with patient clinical parameters for the differential diagnosis between HCC and ICC. The performance of CEUS-CD-Net was evaluated using the area under the receiver operating characteristic curve (AUC), with comparisons against other methods including the single-source data-based models (CEUS-Net and CD-Net, based merely on dynamic CEUS or patient clinical data), CEUS static image-based model (sCEUS-Net), time-intensity curve-based model (TIC-Model), and the assessment by radiologists.
RESULTS: CEUS-CD-Net achieved an AUC of 0.884 (95% CI, 0.794-0.938) on the test cohort, significantly outperforming the single-source data-based models of CEUS-Net (0.827 [0.730-0.896]) and CD-Net (0.812 [0.718-0.887]), as well as sCEUS-Net (0.772 [0.669-0.851]) and TIC-Model (0.731 [0.633-0.823]). In the subset of determinate cases, CEUS-CD-Net achieved an AUC of 0.893 [0.806-0.950], which was better than the one obtained by radiologists' assessment (0.790 [0.683-0.868]). Model visualization results revealed that CEUS-CD-Net surpassed radiologists in discerning subtle patterns reflected by CEUS.
CONCLUSION: The integration of spatial and temporal features of dynamic CEUS data, coupled with clinical parameters of patients in CEUS-CD-Net, significantly improved the differential diagnosis between HCC and ICC.
引用
- Li W, Liu Z, Cheng M, et al. Deep learning model integrating contrast-enhanced ultrasound spatiotemporal imaging with clinical data for the differential diagnosis between hepatocellular carcinoma and intrahepatic cholangiocarcinoma. Radiol Med. 2025. PMID: 41148561. doi:10.1007/s11547-025-02132-6
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。