Adjunct Research Associate, Valleywise Health Medical Center, Phoenix, AZ, United States of America.
Department of Radiology, Valleywise Health Medical Center, Phoenix, AZ, United States of America.
Clin Imaging. 2021 Sep;77:62-68. doi: 10.1016/j.clinimag.2021.02.038. Epub 2021 Feb 23.
Prevalence of nonalcoholic fatty liver disease (NAFLD) in children is rising with the epidemic of childhood obesity. Our objective was to perform digital image analysis (DIA) of ultrasound (US) images of the liver to develop a machine learning (ML) based classification model capable of differentiating NAFLD from healthy liver tissue and compare its performance with pixel intensity-based indices.
De-identified hepatic US images obtained as part of a cross-sectional study examining pediatric NAFLD prevalence were used to build an image database. Texture features were extracted from a representative region of interest (ROI) selected from US images of subjects with normal liver and subjects with confirmed NAFLD using ImageJ and MAZDA image analysis software. Multiple ML classification algorithms were evaluated.
Four-hundred eighty-four ROIs from images in 93 normal subjects and 260 ROIs from images in 39 subjects with NAFLD with 28 texture features extracted from each ROI were used to develop, train, and internally validate the model. An ensembled ML model comprising Support Vector Machine, Neural Net, and Extreme Gradient Boost algorithms was accurate in differentiating NAFLD from normal when tested in an external validation cohort of 211 ROIs from images in 42 children. The texture-based ML model was also superior in predictive accuracy to ML models developed using the intensity-based indices (hepatic-renal index and the hepatic echo-intensity attenuation index).
ML-based predictive models can accurately classify NAFLD US images from normal liver images with high accuracy using texture analysis features.
随着儿童肥胖症的流行，儿童非酒精性脂肪性肝病（NAFLD）的患病率正在上升。我们的目的是对肝脏的超声（US）图像进行数字图像分析（DIA），以开发一种基于机器学习（ML）的分类模型，能够将 NAFLD 与健康的肝组织区分开来，并比较其与基于像素强度的指标的性能。
使用从横断面研究中获得的、用于检查儿科 NAFLD 患病率的肝 US 图像的匿名数据集来构建图像数据库。使用 ImageJ 和 MAZDA 图像分析软件从正常肝和经证实的 NAFLD 患者的 US 图像中选择的代表性感兴趣区域（ROI）中提取纹理特征。评估了多种 ML 分类算法。
从 93 名正常受试者的图像中提取了 484 个 ROI，从 39 名 NAFLD 受试者的图像中提取了 260 个 ROI，从每个 ROI 中提取了 28 个纹理特征，用于开发、训练和内部验证模型。一个由支持向量机、神经网络和极端梯度提升算法组成的集成 ML 模型在对 42 名儿童的 211 个 ROI 的图像进行外部验证时，能够准确地区分 NAFLD 和正常。基于纹理的 ML 模型在预测准确性方面也优于使用基于强度的指标（肝-肾指数和肝回声强度衰减指数）开发的 ML 模型。
基于 ML 的预测模型可以使用纹理分析特征准确地对 NAFLD US 图像与正常肝图像进行分类，具有很高的准确性。
