文献速递腹部技术与安全US

深度学习整合超声微血流动态、B超图像与临床参数诊断慢乙肝显著肝纤维化

A deep learning model with data integration of ultrasound contrast-enhanced micro-flow cines, B-mode images, and clinical parameters for diagnosing significant liver fibrosis in patients with chronic hepatitis B.
PubMed 文献 · Eur Radiol · 2023-02-03

本研究基于218例慢性乙型肝炎患者,构建整合超声造影微血流(CEMF)动态、B超图像和临床参数的深度学习模型(DIDL),用于诊断显著肝纤维化(≥F2)。五折交叉验证显示DIDL模型平均AUC为0.901,显著高于单一数据模型、常规TIC法、APRI、FIB-4及两位放射科医生的视觉评估。

要点

  • DIDL模型诊断≥F2的AUC为0.901,优于单一CEMF、B超、临床数据模型及常规方法。
  • 融合多模态数据(CEMF cine、B超、临床参数)可提升显著肝纤维化诊断效能。
  • 特征注意力图有助于理解肝纤维化相关影像特征,辅助放射科医生诊断。

局限性

  • 回顾性研究设计。
  • 单中心研究。

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

OBJECTIVE: To develop and investigate a deep learning model with data integration of ultrasound contrast-enhanced micro-flow (CEMF) cines, B-mode images, and patients' clinical parameters to improve the diagnosis of significant liver fibrosis (≥ F2) in patients with chronic hepatitis B (CHB).

METHODS: Of 682 CHB patients who underwent ultrasound and histopathological examinations between October 2016 and May 2020, 218 subjects were included in this retrospective study. We devised a data integration-based deep learning (DIDL) model for assessing ≥ F2 in CHB patients. The model contained three convolutional neural network branches to automatically extract features from ultrasound CEMF cines, B-mode images, and clinical data. The extracted features were fused at the backend of the model for decision-making. The diagnostic performance was evaluated across fivefold cross-validation and compared against the other methods in terms of the area under the receiver operating characteristic curve (AUC), with histopathological results as the reference standard.

RESULTS: The mean AUC achieved by the DIDL model was 0.901 [95% CI, 0.857-0.939], which was significantly higher than those of the comparative methods, including the models trained by using only CEMF cines (0.850 [0.794-0.893]), B-mode images (0.813 [0.754-0.862]), or clinical data (0.757 [0.694-0.812]), as well as the conventional TIC method (0.752 [0.689-0.808]), APRI (0.792 [0.734-0.845]), FIB-4 (0.776 [0.714-0.829]), and visual assessments of two radiologists (0.812 [0.754-0.862], and 0.800 [0.739-0.849]), all ps < 0.01, DeLong test.

CONCLUSION: The DIDL model with data integration of ultrasound CEMF cines, B-mode images, and clinical parameters showed promising performance in diagnosing significant liver fibrosis for CHB patients.

KEY POINTS: • The combined use of ultrasound contrast-enhanced micro-flow cines, B-mode images, and clinical data in a deep learning model has potential to improve the diagnosis of significant liver fibrosis. • The deep learning model with the fusion of features extracted from multimodality data outperformed the conventional methods including mono-modality data-based models, the time-intensity curve-based recognizer, fibrosis biomarkers, and visual assessments by experienced radiologists. • The interpretation of the feature attention maps in the deep learning model may help radiologists get better understanding of liver fibrosis-related features and hence potentially enhancing their diagnostic capacities.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Liu, Li, Zhu, et al. A deep learning model with data integration of ultrasound contrast-enhanced micro-flow cines, B-mode images, and clinical parameters for diagnosing significant liver fibrosis in patients with chronic hepatitis B. Eur Radiol. 2023. PMID: 36735040. doi:10.1007/s00330-023-09436-z

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。