Mihăilescu Dan Mihai, Gui Vasile, Toma Corneliu Ioan, Popescu Alina, Sporea Ioan
Department of Telecommunications, Faculty of Electronics and Telecommunications, Politehnica University, Romania.
Med Ultrason. 2013 Sep;15(3):184-90. doi: 10.11152/mu.2013.2066.153.dmm1vg2.
In this paper we discuss the problem of computer aided evaluation of the severity of steatosis disease using ultrasound images. The AIM of the study being to compare the automatic evaluation of liver steatosis using random forests (RF) and support vector machine (SVM) classifiers.
One hundred and twenty consecutive patients with steatosis or normal liver, assessed by ultrasound by the same expert, were enrolled. We graded steatosis in four stages and trained two classifiers to rate the severity of disease, based on a large set of labeled images and a large set of features, including several features obtained by robust estimation techniques. We compared RF and SVM classifiers. The classifiers were trained using cross-validation. There was 80% of data randomly selected for training and 20% for testing the classifier. This procedure was performed 20 times. The main measure of performance was the accuracy.
From all cases, 10 were rated as normal liver, 70 as having mild, 33 moderate, and 7 severe steatosis. Our best experts' ratings were used as ground truth data. RF outperformed the SVM classifier and confirmed the ability of this classifier to perform well without feature selection. In contrast, the performance of the SVM classifier was poor without feature selection and improved significantly after feature selection.
The ability and accuracy of RF to classify well the steatosis severity, without feature selection, were superior as compared to SVM.
在本文中，我们讨论了使用超声图像对脂肪变性疾病严重程度进行计算机辅助评估的问题。该研究的目的是比较使用随机森林（RF）和支持向量机（SVM）分类器对肝脏脂肪变性进行自动评估的情况。
招募了120名连续的患有脂肪变性或肝脏正常的患者，由同一位专家通过超声进行评估。我们将脂肪变性分为四个阶段，并基于大量标记图像和大量特征（包括通过稳健估计技术获得的几个特征）训练两个分类器来评估疾病的严重程度。我们比较了RF和SVM分类器。分类器使用交叉验证进行训练。随机选择80%的数据用于训练，20%的数据用于测试分类器。此过程进行了20次。性能的主要衡量指标是准确性。
在所有病例中，10例被评为肝脏正常，70例为轻度脂肪变性，33例为中度脂肪变性，7例为重度脂肪变性。我们最好的专家评级被用作真实数据。RF的表现优于SVM分类器，并证实了该分类器在不进行特征选择的情况下也能表现良好的能力。相比之下，SVM分类器在不进行特征选择时性能较差，在进行特征选择后有显著改善。
与SVM相比，RF在不进行特征选择的情况下对脂肪变性严重程度进行良好分类的能力和准确性更优。
