深度学习分析MRI准确检测原发性硬化性胆管炎患者的早期肝门部胆管癌
这项国际多中心回顾性队列研究纳入398例大胆管型原发性硬化性胆管炎(PSC)成人患者,训练3D DenseNet-121深度学习模型分析MRI图像,并在独立测试队列中与专家放射科医生比较诊断性能。模型检测早期肝门部胆管癌(pCCA)的敏感度87.9% vs 放射科医生50.0%、特异度84.1% vs 100.0%、AUC 86.0% vs 75.0%,差异均有统计学意义;无肿块时模型敏感度仍更高(91.6% vs 50.6%)。
要点
- 测试队列中模型检测早期pCCA敏感度87.9%,高于放射科医生的50.0%(p<0.001)。
- 模型特异度84.1%,低于放射科医生的100.0%(p<0.001)。
- 无肿块时模型敏感度91.6% vs 放射科医生50.6%(p<0.001),特异度维持84.1%。
核心结论
- 3D DenseNet-121 MRI模型能有效检测PSC患者的早期pCCA,与专家放射科医生相比遗漏的癌症病例更少。
研究设计与样本
- 国际多中心回顾性队列研究,纳入接受增强MRI的大胆管型PSC成人患者,所有pCCA患者均为早期癌症并登记肝移植。
- 研究共纳入398例患者(训练队列n=150;测试队列n=248),其中pCCA患者230例(训练队列n=64;测试队列n=166)。
- 使用MRI图像训练3D DenseNet-121深度学习模型,并在独立测试队列中评估性能,由资深腹部放射科医生阅片作为对照。
主要发现
- 测试队列中,模型 vs 放射科医生的敏感度为87.9% vs 50.0%(p<0.001),特异度为84.1% vs 100.0%(p<0.001),受试者工作特征曲线下面积为86.0% vs 75.0%(p<0.001)。
- 无肿块时,模型对pCCA的敏感度为91.6% vs 放射科医生50.6%(p<0.001),并维持良好特异度84.1%。
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)。
原文
BACKGROUND AND AIMS: Among those with primary sclerosing cholangitis (PSC), perihilar cholangiocarcinoma (pCCA) is often diagnosed at a late stage and is a leading source of mortality. Detection of pCCA in PSC when curative action can be taken is challenging. Our aim was to create a deep learning model that analyzed MRI to detect early-stage pCCA and compare its diagnostic performance with expert radiologists. APPROACH AND RESULTS: We conducted a multicenter, international, retrospective cohort study involving adults with large duct PSC who underwent contrast-enhanced MRI. Senior abdominal radiologists reviewed the images. All patients with pCCA had early-stage cancer and were registered for liver transplantation. We trained a 3D DenseNet-121 model, a form of deep learning, using MRI images and assessed its performance in a separate test cohort. The study included 398 patients (training cohort n=150; test cohort n=248). pCCA was present in 230 individuals (training cohort n=64; test cohort n=166). In the test cohort, the respective performances of the model compared to the radiologists were: sensitivity 87.9% versus 50.0%, p <0.001; specificity 84.1% versus 100.0%, p <0.001; area under receiving operating curve 86.0% versus 75.0%, p <0.001. Even when a mass was absent, the model had a higher sensitivity for pCCA than radiologists (91.6% vs. 50.6%, p <0.001) and maintained good specificity (84.1%). CONCLUSIONS: The 3D DenseNet-121 MRI model effectively detects early-stage pCCA in PSC patients. Compared to expert radiologists, the model missed fewer cases of cancer.
引用
- Singh Y, Eaton JE, Venkatesh SK, et al. Deep learning analysis of MRI accurately detects early-stage perihilar cholangiocarcinoma in patients with primary sclerosing cholangitis. Hepatology. 2025. PMID: 40112296. doi:10.1097/HEP.0000000000001314
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。