文献速递腹部MR

基于三维磁共振胰胆管成像使用机器学习全自动检测原发性硬化性胆管炎(PSC)兼容性胆管改变

Fully automated detection of primary sclerosing cholangitis (PSC)-compatible bile duct changes based on 3D magnetic resonance cholangiopancreatography using machine learning.
PubMed 文献 · Eur Radiol · 2020-09-24

本研究回顾性纳入428例(205例确诊PSC,223例非PSC)行含MRCP的MRI检查患者,随机分为训练组386例和验证组42例,开发并评估深度学习算法在3D-MRCP图像上全自动检测PSC兼容性胆管改变。采用集成策略后平均绝对误差从21%降至7.1%,敏感度95.0%、特异度90.9%、阳性预测值90.5%、阴性预测值95.2%。结论提示该算法检测PSC兼容性胆管改变具有高敏感度和低平均绝对误差,但需更多多中心数据进一步验证。

要点

  • 集成策略使PSC兼容性胆管改变检测的平均绝对误差从21%降至7.1%。
  • 验证集敏感度95.0%、特异度90.9%、阳性预测值90.5%、阴性预测值95.2%。
  • 从3D数据集生成2D投影可实现集成策略以提升推理性能。

核心结论

  • 迁移学习结合广泛图像增强可在3D-MRCP图像上检测PSC兼容性胆管改变,具有高敏感度和低平均绝对误差。
  • 作者认为需要更多多中心数据进一步验证,因为神经网络倾向于过拟合数据集特征。

研究设计与样本

  • 回顾性IRB批准研究,纳入428例转诊行含MRCP的MRI检查患者,其中205例确诊PSC、223例非PSC。
  • 数据集随机分为训练组386例和验证组42例;每例计算20个均匀分布的轴位MRCP旋转及随后的最大强度投影(MIP),得到训练数据库7720幅图像和验证数据库840幅图像。
  • 采用预训练的Inception ResNet进行微调(学习率10^-3)。

诊断标准与关键数值

  • 应用集成策略(对20个轴位投影进行分箱)后,检测PSC兼容性胆管改变的平均绝对误差从21%降至7.1%。
  • 检测PSC兼容性胆管改变的敏感度95.0%、特异度90.9%、阳性预测值90.5%、阴性预测值95.2%。

临床应用与阅片要点

  • 该算法可在3D-MRCP图像上全自动检测PSC兼容性胆管改变,验证集敏感度95.0%、特异度90.9%。
  • 从3D数据集生成2D投影并采用集成策略可提升推理性能,平均绝对误差从21%降至7.1%。

局限性

  • 作者指出需要更多多中心数据进一步验证,因为神经网络倾向于过拟合数据集特征。

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

OBJECTIVES: To develop and evaluate a deep learning algorithm for fully automated detection of primary sclerosing cholangitis (PSC)-compatible cholangiographic changes on three-dimensional magnetic resonance cholangiopancreatography (3D-MRCP) images.

METHODS: The datasets of 428 patients (n = 205 with confirmed diagnosis of PSC; n = 223 non-PSC patients) referred for MRI including MRCP were included in this retrospective IRB-approved study. Datasets were randomly assigned to a training (n = 386) and a validation group (n = 42). For each case, 20 uniformly distributed axial MRCP rotations and a subsequent maximum intensity projection (MIP) were calculated, resulting in a training database of 7720 images and a validation database of 840 images. Then, a pre-trained Inception ResNet was implemented which was conclusively fine-tuned (learning rate 10-3).

RESULTS: Applying an ensemble strategy (by binning of the 20 axial projections), the mean absolute error (MAE) of the developed deep learning algorithm for detection of PSC-compatible cholangiographic changes was lowered from 21 to 7.1%. Sensitivity, specificity, positive predictive (PPV), and negative predictive value (NPV) for detection of these changes were 95.0%, 90.9%, 90.5%, and 95.2% respectively.

CONCLUSIONS: The results of this study demonstrate the feasibility of transfer learning in combination with extensive image augmentation to detect PSC-compatible cholangiographic changes on 3D-MRCP images with a high sensitivity and a low MAE. Further validation with more and multicentric data is now desirable, as it is known that neural networks tend to overfit the characteristics of the dataset.

KEY POINTS: • The described machine learning algorithm is able to detect PSC-compatible cholangiographic changes on 3D-MRCP images with high accuracy. • The generation of 2D projections from 3D datasets enabled the implementation of an ensemble strategy to boost inference performance.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Ringe KI, Vo Chieu VD, Wacker F, et al. Fully automated detection of primary sclerosing cholangitis (PSC)-compatible bile duct changes based on 3D magnetic resonance cholangiopancreatography using machine learning. Eur Radiol. 2020. PMID: 32974688. doi:10.1007/s00330-020-07323-5

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。