Sánchez Clara I, Mayo Agustín, García María, López María I, Hornero Roberto
Dept. of Signal Theor. & Commun., Valladolid Univ., Spain.
Conf Proc IEEE Eng Med Biol Soc. 2006;2006:4453-6. doi: 10.1109/IEMBS.2006.260434.
Automatic detection of hard exudates from retinal images is clinically significant. Hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest clinical signs of retinopathy. In this study, an automatic method to detect hard exudates is proposed. The algorithm is based on mixture models to dynamically threshold the images in order to separate hard exudates from background. We prospectively assessed the algorithm performance using a database of 20 retinal images with variable color, brightness, and quality. The algorithm obtained a sensitivity of 90.23% and a predictive value of 82.5% using a lesion-based criterion. The image-based classification accuracy is also evaluated obtaining a sensitivity of 100% and a specificity of 90%
从视网膜图像中自动检测硬性渗出物具有临床意义。硬性渗出物与糖尿病视网膜病变相关，并且已被发现是视网膜病变最常见的最早临床体征之一。在本研究中，提出了一种检测硬性渗出物的自动方法。该算法基于混合模型对图像进行动态阈值处理，以便将硬性渗出物与背景分离。我们使用包含20张具有不同颜色、亮度和质量的视网膜图像的数据库对该算法性能进行了前瞻性评估。使用基于病变的标准，该算法获得了90.23%的灵敏度和82.5%的预测值。还评估了基于图像的分类准确性，获得了100%的灵敏度和90%的特异性。
