Department of Biomedical Engineering, University of Iowa, Iowa City, IA, USA.
Invest Ophthalmol Vis Sci. 2012 Sep 25;53(10):6582-8. doi: 10.1167/iovs.12-10191.
To develop an automated method for the detection of retinal hemorrhages on color fundus images to characterize malarial retinopathy, which may help in the assessment of patients with cerebral malaria.
A fundus image dataset from 14 patients (200 fundus images, with an average of 14 images per patient) previously diagnosed with malarial retinopathy was examined. We developed a pattern recognition-based algorithm, which extracted features from image watershed regions called splats (tobogganing). A reference standard was obtained by manual segmentation of hemorrhages, which assigned a label to each splat. The splat features with the associated splat label were used to train a linear k-nearest neighbor classifier that learnt the color properties of hemorrhages and identified the splats belonging to hemorrhages in a test dataset. In a crossover design experiment, data from 12 patients were used for training and data from two patients were used for testing, with 14 different permutations; and the derived sensitivity and specificity values were averaged.
The experiment resulted in hemorrhage detection sensitivities in terms of splats as 80.83%, and in terms of lesions as 84.84%. The splat-based specificity was 96.67%, whereas for the lesion-based analysis, an average of three false positives was obtained per image. The area under the receiver operating characteristic curve was reported as 0.9148 for splat-based, and as 0.9030 for lesion-based analysis.
The method provides an automated means of detecting retinal hemorrhages associated with malarial retinopathy. The results matched well with the reference standard. With further development, this technique may provide automated assistance for screening and quantification of malarial retinopathy.
开发一种用于彩色眼底图像中视网膜出血检测的自动化方法，以对疟疾性视网膜病变进行特征描述，这可能有助于评估脑型疟疾患者。
检查了来自 14 名（200 张眼底图像，每位患者平均有 14 张图像）先前被诊断患有疟疾性视网膜病变的患者的眼底图像数据集。我们开发了一种基于模式识别的算法，该算法从称为 tobogganing 的分水岭区域的图像中提取特征（splats）。通过手动对出血进行分割获得参考标准，为每个 splat 分配一个标签。使用带有相关 splat 标签的 splat 特征来训练线性 k-最近邻分类器，该分类器学习出血的颜色特性，并识别测试数据集中属于出血的 splat。在交叉设计实验中，使用 12 名患者的数据进行训练，使用两名患者的数据进行测试，有 14 种不同的排列；并平均得出敏感性和特异性值。
实验得出了以 splat 为单位的出血检测敏感性为 80.83%，以病变为单位的敏感性为 84.84%。基于 splat 的特异性为 96.67%，而基于病变的分析中，每张图像平均有三个假阳性。基于 splat 的受试者工作特征曲线下面积为 0.9148，基于病变的分析为 0.9030。
该方法提供了一种自动检测与疟疾性视网膜病变相关的视网膜出血的手段。结果与参考标准吻合良好。随着进一步的发展，该技术可能为疟疾性视网膜病变的筛查和定量提供自动辅助。
