Grupo de Ingeniería Biomédica, E.T.S. Ingenieros de Telecomunicación, University of Valladolid, Paseo Belén 15, 47011 Valladolid, Spain.
Med Eng Phys. 2010 Dec;32(10):1085-93. doi: 10.1016/j.medengphy.2010.07.014. Epub 2010 Aug 23.
Diabetic retinopathy (DR) is an important cause of visual impairment in industrialised countries. Automatic detection of DR early markers can contribute to the diagnosis and screening of the disease. The aim of this study was to automatically detect one of such early signs: red lesions (RLs), like haemorrhages and microaneurysms. To achieve this goal, we extracted a set of colour and shape features from image regions and performed feature selection using logistic regression. Four neural network (NN) based classifiers were subsequently used to obtain the final segmentation of RLs: multilayer perceptron (MLP), radial basis function (RBF), support vector machine (SVM) and a combination of these three NNs using a majority voting (MV) schema. Our database was composed of 115 images. It was divided into a training set of 50 images (with RLs) and a test set of 65 images (40 with RLs and 25 without RLs). Attending to performance and complexity criteria, the best results were obtained for RBF. Using a lesion-based criterion, a mean sensitivity of 86.01% and a mean positive predictive value of 51.99% were obtained. With an image-based criterion, a mean sensitivity of 100%, mean specificity of 56.00% and mean accuracy of 83.08% were achieved.
糖尿病性视网膜病变（DR）是工业化国家视力损害的重要原因。自动检测 DR 的早期标志物有助于疾病的诊断和筛查。本研究的目的是自动检测其中一种早期迹象：红色病变（RLs），如出血和微动脉瘤。为了实现这一目标，我们从图像区域中提取了一组颜色和形状特征，并使用逻辑回归进行特征选择。随后使用四个基于神经网络（NN）的分类器来获得 RL 的最终分割：多层感知器（MLP）、径向基函数（RBF）、支持向量机（SVM）以及使用多数投票（MV）方案组合这三个神经网络。我们的数据库由 115 张图像组成。它分为一个包含 50 张图像（有 RLs）的训练集和一个包含 65 张图像（40 张有 RLs，25 张没有 RLs）的测试集。根据性能和复杂性标准，RBF 获得了最佳结果。使用基于病变的标准，获得了 86.01%的平均敏感性和 51.99%的平均阳性预测值。使用基于图像的标准，实现了 100%的平均敏感性、56.00%的平均特异性和 83.08%的平均准确性。
