Department of Radiology, University of California, La Jolla, California, USA.
Department of Ultrasound, Institute of Fundamental Technological Research, Polish Academy of Sciences, Warsaw, Poland.
J Ultrasound Med. 2022 Jan;41(1):175-184. doi: 10.1002/jum.15693. Epub 2021 Mar 10.
To develop and evaluate deep learning models devised for liver fat assessment based on ultrasound (US) images acquired from four different liver views: transverse plane (hepatic veins at the confluence with the inferior vena cava, right portal vein, right posterior portal vein) and sagittal plane (liver/kidney).
US images (four separate views) were acquired from 135 participants with known or suspected nonalcoholic fatty liver disease. Proton density fat fraction (PDFF) values derived from chemical shift-encoded magnetic resonance imaging served as ground truth. Transfer learning with a deep convolutional neural network (CNN) was applied to develop models for diagnosis of fatty liver (PDFF ≥ 5%), diagnosis of advanced steatosis (PDFF ≥ 10%), and PDFF quantification for each liver view separately. In addition, an ensemble model based on all four liver view models was investigated. Diagnostic performance was assessed using the area under the receiver operating characteristics curve (AUC), and quantification was assessed using the Spearman correlation coefficient (SCC).
The most accurate single view was the right posterior portal vein, with an SCC of 0.78 for quantifying PDFF and AUC values of 0.90 (PDFF ≥ 5%) and 0.79 (PDFF ≥ 10%). The ensemble of models achieved an SCC of 0.81 and AUCs of 0.91 (PDFF ≥ 5%) and 0.86 (PDFF ≥ 10%).
Deep learning-based analysis of US images from different liver views can help assess liver fat.
开发并评估基于来自四个不同肝脏切面的超声（US）图像的肝脏脂肪评估深度学习模型，这四个切面分别是：横切面（肝静脉与下腔静脉汇合处、右门静脉、右后门静脉）和矢状面（肝脏/肾脏）。
从 135 名已知或疑似非酒精性脂肪肝疾病的参与者中获取 US 图像（四个单独的切面）。化学位移编码磁共振成像得出的质子密度脂肪分数（PDFF）值作为金标准。应用迁移学习的深度卷积神经网络（CNN）来开发用于诊断脂肪肝（PDFF≥5%）、诊断严重脂肪变性（PDFF≥10%）和单独对每个肝脏切面进行 PDFF 定量的模型。此外，还研究了基于所有四个肝脏切面模型的集成模型。使用接收器操作特征曲线下的面积（AUC）评估诊断性能，使用斯皮尔曼相关系数（SCC）评估定量性能。
最准确的单一切面是右后门静脉，其用于定量 PDFF 的 SCC 为 0.78，AUC 值分别为 0.90（PDFF≥5%）和 0.79（PDFF≥10%）。模型的集成达到了 0.81 的 SCC 和 0.91（PDFF≥5%）和 0.86（PDFF≥10%）的 AUC。
基于深度学习的不同肝脏切面 US 图像分析可帮助评估肝脏脂肪。
